Home •Blog
TTMS Blog
TTMS experts about the IT world, the latest technologies and the solutions we implement.
Sort by topics
Best Practices for Adobe Experience Manager Implementation
AEM implementation best practices for architecture, deployment, asset governance and author adoption. Plan your Adobe Experience Manager project with TTMS.
Read
AI in GxP Environments: From Pilot to Validated Deployment
Misclassifying a document can cause an important record to be filed in the wrong place within a system. In the pharmaceutical industry, such an error has implications for data integrity and the handling of regulated documentation. This was one of the examples discussed during the “Deploying AI in the GxP World” webinar, illustrating how many decisions need to be made before artificial intelligence can support day-to-day work in a GxP environment. On 13 October 2026, we attended the “Deploying AI in the GxP World” webinar, organised by ISPE Poland together with ProductLife Group (PLG). Naomi Ofili and Gabrièle Piaton from PLG spoke at the event. They discussed the risk assessment, validation and safeguards needed to move from an AI pilot to a deployment whose operation can be documented and assessed during an inspection. The webinar formed part of a series linked to the AI in Pharma 2026 conference. 1. What is GxP, and how does it affect AI deployment in pharma? GxP is an umbrella term for good practices covering areas such as medicinal product manufacturing, clinical trials and pharmacovigilance. One of the webinar’s central messages was that assessing an AI application should begin with its intended use and impact on a specific process. The same model can support tasks with very different implications for product quality, patient safety and documentation. The speakers illustrated this through translation. Translating internal correspondence and translating product information submitted to regulatory authorities require separate assessments. The same applies to literature analysis: the requirements depend on whether the search supports market monitoring or the identification of information about medicine safety. How the AI output is subsequently used also matters. Text, classifications or metadata may become part of regulated documentation. The assessment should therefore consider the solution’s role in the process, its impact on GxP records and the consequences of an error. The speakers recommended carrying out this analysis when developing the project’s business case, so that the validation scope, resources and costs can be identified early. 2. AI validation needs to be planned across the operational lifecycle Validation provides documented evidence that a system is fit for its intended use. The webinar repeatedly returned to the question of how to demonstrate this suitability for AI. The speakers referred to the risk-based approach described in GAMP 5 and to guidance on artificial intelligence. The materials cited included the ISPE GAMP Guide: Artificial Intelligence, published in 2025, which addresses AI-enabled systems in GxP areas. Another reference was the European Medicines Agency’s reflection paper on AI in the medicinal product lifecycle. The practical questions concerned data and evaluation criteria. Do the test examples reflect real documents and products? Was the test dataset independent of the data used to tune the solution? Which results will we consider acceptable, and did we define these criteria before testing began? The approach presented also covered limiting outputs unsupported by source material, assessing behavioural stability, monitoring performance, handling invalid inputs and detecting bias. Testing before release was combined with controls during operation and assessment of the impact of model changes. Reference collections of test cases developed with subject matter experts, described during the presentation as golden sets, can help. Revisiting the same cases across successive versions of a solution makes it possible to check whether a change has reduced performance on tasks that matter to the organisation. We explore practical ways to support testing and quality documentation in our comparison of AI QA tools for pharma. 3. Human oversight extends beyond approving an output Naomi Ofili distinguished between two levels of human involvement. The first is human-in-the-loop: a stage in the process at which an expert approves, edits or rejects an AI output. The second is oversight across the solution’s entire lifecycle, including monitoring, preventing uncritical acceptance of automated outputs and the ability to stop the system. In the workflow described, the AI output underwent automated checks before being reviewed by a designated expert. Information about the sources, instructions given to the model, its version and the approval was retained. This record made it possible to reconstruct the conditions under which the output was produced and identify who approved its use. The expert also helped define acceptance criteria and develop test cases. Their knowledge therefore informed the solution’s design and the way its quality was assessed. For a company planning a deployment, this means assigning responsibilities and allocating time for expert involvement from the outset. 4. What did the examples of literature monitoring, translation and data migration show? The speakers illustrated these principles with three examples from projects carried out by the PLG team. Each highlighted different requirements for assessing AI outputs and their subsequent use. 4.1. Literature monitoring for pharmacovigilance In the first example, AI supported the review of scientific publications for pharmacovigilance. The system proposed a category for each article and a rationale, both of which were reviewed by an expert. Gabrièle Piaton emphasised that a particularly challenging step was translating the specialists’ assessment method into a structured decision tree. This example showed the importance of documenting expert knowledge and classification criteria before automating a task. 4.2. Translation of regulated documentation The second example concerned AI-assisted translation reviewed by a human against quality criteria tailored to the risk associated with the document. The process also included reconstructing the formatting to facilitate the translators’ subsequent work. Assessment of the solution therefore covered content quality, the review process and the document’s suitability for further use. 4.3. Data migration and document classification In the third example, AI supported document classification, metadata extraction and mapping data to the target system’s structure. The speakers highlighted the difficulty of distinguishing between similar document classes and the consequences of misclassification. They stressed the need to trace data provenance, transformations and approvals, as well as to perform quantitative and qualitative verification before migrated data are put into use. 5. Hosting and costs should be considered before the pilot A separate part of the webinar focused on solution architecture. The speakers suggested deciding before the pilot where data would be processed, what information would be recorded in logs and whether the model version could be controlled. Their criteria for selecting an environment included confidentiality, data-processing location, update arrangements, the ability to reconstruct system activity and the cost of switching suppliers. The discussion also covered selecting models for individual tasks. Smaller, specialised models can help reduce costs if they meet the defined quality requirements. The proposed economic assessment focused on the cost of completing a task and obtaining the expected result. The speakers also highlighted the possibility of reusing components for information retrieval, testing, monitoring and output approval. We discuss the division of responsibilities between a pharmaceutical company and its supplier, along with update controls, in more detail in our article on SaaS validation in pharma and GxP requirements. 6. What helps move an AI pilot into day-to-day operation? Towards the end of the session, the speakers highlighted collaboration between technical teams, subject matter experts and the customer around a jointly agreed backlog. They also stressed the importance of appointing a business owner responsible for adoption of the solution and measurement of its outcomes. The experiences presented suggested a sequence of activities: defining the intended use and responsibilities, assessing risk, designing controls, building and validating the solution, and then maintaining it. Decisions about data quality, human oversight and change management affect every stage. For companies preparing a deployment, this means resolving several questions before the pilot: what task will AI perform, who will approve its outputs, how will their quality be assessed, and what will happen if the model or data source changes? The answers help teams plan the technical work, validation requirements and ongoing maintenance. 7. How does TTMS support deployments in pharmaceutical environments? Translating these decisions into requirements, tests and documentation requires collaboration between people who understand the business process, technology and quality assurance. At TTMS, we combine software development and maintenance for the pharmaceutical industry with TTMS Quality’s expertise in computerised system validation. Our validation services cover validation planning, requirements specification and review, test development and execution, results assessment and reporting. We use a risk-based approach and GAMP 5 guidance. The scope of work is tailored to the system’s intended use and the requirements of the specific process. If you are planning to use AI in a pharmaceutical process or preparing to take a pilot further, talk to our specialists about your solution’s requirements, risks and validation scope. Can an AI pilot in pharma start with synthetic data? Yes, synthetic data can help test an initial concept without using actual patient data or confidential documentation. However, they should reflect the structure, diversity and challenges of the intended application. Overly simple examples can give a misleading impression of the solution’s quality. It is worth including missing information, errors and ambiguous cases. The results of such a pilot are insufficient to demonstrate that the system is suitable for a real GxP process. Further assessment requires representative test data, agreed acceptance criteria and controls proportionate to risk. What should you do when AI and an expert assess the same document differently? The discrepancy should be reviewed according to an established procedure. The source document, AI output, solution version and the expert’s assessment and rationale should be retained. The cause may be a model error, ambiguous content or evaluation criteria that are too broad. Such cases help determine whether instructions, classification rules or tests need to change. An expert’s correction should not automatically trigger an update to a model used in a regulated process. Any change should be assessed, tested and approved, while retaining an independent dataset for quality evaluation. How should employees be prepared to use AI in pharmaceutical processes? Training should address the specific task, data and scope of the user’s responsibilities. Employees need to know what information they may submit to the system, how to check outputs and when to raise concerns. Exercises involving incorrect, incomplete or seemingly convincing responses are useful. They help assess whether users can verify an output rather than accept it uncritically. Instructions for handling failures or periods when the solution is unavailable are also helpful. Team preparation should include an assessment of practical skills, and training should be updated when the system or procedures change.
Read
Artificial Intelligence in Education: How AI Supports Learning and Training in the Workplace
Corporate L&D departments face a major challenge: how to develop effective training faster while maintaining high course quality. Artificial intelligence in education and training can significantly accelerate this process by generating course drafts from source documents. AI prepares the first draft, while subject matter experts review and refine the generated materials. This can reduce course development time from weeks to hours. How generative AI in education transforms corporate training E-learning courses have often been developed as one-off projects. Teams gathered materials, wrote a script and built the module, but the content could soon become outdated after publication. Artificial intelligence in learning supports a more continuous approach: an AI tool prepares the first draft, and a subject matter expert reviews, updates and approves the content. For L&D departments, this means a shorter path from identifying a business need to delivering a training programme and fewer hours spent on repetitive course development tasks. These two contexts must be distinguished. In schools and universities, AI supports the teacher and the student (as discussed in our article on AI in higher education). In corporate learning, AI helps reduce the time needed to develop employee training and supports consistent quality across different languages and cultural contexts. Organisations planning to use AI more widely usually start by defining their objectives and assessing the data available to them. If you want to learn more, visit our page on AI solutions for business. AI in education: benefits for course development time and costs Much of the cost of developing an e-learning course comes from gathering expert input, structuring the content and creating exercises. Artificial intelligence in training can shorten this stage by using source materials in DOC, PDF or PPT formats to generate a structured first draft of the course, complete with exercises and versions in different languages. AI4E-learning is an AI-powered tool for creating e-learning courses from source documents. It generates a structured draft that a subject matter expert can review and refine before exporting the approved course as a SCORM-compliant package for use in an existing LMS. Every element remains editable, giving the expert control over the course’s scope, factual accuracy and final content. This can significantly shorten course development time and help L&D teams deliver training sooner. With less time spent on repetitive production tasks, experts can focus on reviewing factual accuracy, refining the content and keeping it up to date. We have gathered practical examples of how to do this in our material on building effective e-learning with AI. AI-powered learning: personalised and adaptive learning paths The same content does not work equally well for every employee. Someone new to a role may need the basics, while a more experienced colleague may be ready for advanced topics. AI can help adapt the pace of learning, level of difficulty and feedback to each employee’s existing knowledge and progress. The AI Center team at the University of Szczecin identifies personalised learning as one of the main benefits of AI in education. In a corporate setting, this can help employees develop the required skills and knowledge more quickly, while reducing the risk of training being too basic or too demanding for some team members. Personalisation also requires careful design. Making learning easier does not necessarily help employees retain what they have learnt, as we discuss in the next section. Our company blog article on e-learning trends explores how corporate learning is evolving. What science says: AI, cognitive load and knowledge retention Faster course development and personalised learning are key benefits of AI. But does easier access to ready-made answers actually help people learn and retain information? Research suggests that this is not always the case. A study by a team of researchers from Carnegie Mellon University and Microsoft Research, led by Hao-Ping Lee (CHI 2025 conference), involved 319 knowledge workers. It turned out that individuals who trusted AI-generated answers more reported less engagement in critical thinking. Similar correlations were observed by Michael Gerlich, a professor at the SBS Swiss Business School, who surveyed 666 people in 2025. More frequent use of AI was associated with a greater tendency to offload cognitive effort onto technology. Both studies indicate a correlation, but they do not prove that AI causes a decline in these skills. Even more interesting conclusions come from an experiment by Bastani and colleagues, published in PNAS in 2025. Students using GPT-4 achieved better results during exercises, but when their access to AI was removed, their performance was worse than the control group. The problem was significantly reduced when the tool guided students through tasks using hints instead of providing ready-made solutions. What does this mean for companies designing training? AI should help employees understand the material, but it should not do the thinking for them. That is why it is worth using knowledge checks, practical exercises and tasks that require recalling previously learned information. This approach supports long-term retention and skill development. We also apply this principle in AI4E-learning, combining AI-generated content with exercises and expert review to create courses that engage learners and help them apply what they have learnt at work. AI is changing education: the role of subject matter experts In AI4E-learning, subject matter experts remain responsible for the quality of the final course. AI generates the initial draft and automates repetitive tasks, while an expert checks factual accuracy, adapts the content to the organisation’s context and approves the final version. This is the human-in-the-loop approach in practice. Control over data is equally important. In this configuration, AI4E-learning uses Azure OpenAI. Data processing and access controls depend on the client’s infrastructure and configuration settings. Responsible use of AI in training therefore requires appropriate technical safeguards alongside expert review of the generated content. This division of roles is visible in specific tasks: Task What AI does What humans decide Course structure proposes the layout of modules and learning objectives approves the scope and sequence Content and exercises generates the first draft from source materials verifies factual accuracy Language versions creates translations and variants approves terminology and context Data operates within the client tenant decides on access and data scope AI applications in learning: a practical example A training project for one of our clients’ helpdesk teams shows how AI can support corporate learning in practice. A traditional presentation was replaced with an interactive course in which employees completed exercises and received feedback tailored to their mistakes. The result was faster, more consistent onboarding for new employees and fewer questions directed to experienced colleagues. The course was developed using the company’s existing materials, and a subject matter expert reviewed each section before publication. We deliver projects like this as part of our e-learning services. AI in online learning: a corporate training case study Using AI in corporate training involves several risks, including inaccurate AI-generated content, inadequate protection of personal data and barriers to accessing training. These risks can be reduced through expert review, appropriate data security measures and regular monitoring of tool performance. Legal requirements must also be considered. The EU AI Act (Regulation 2024/1689) classifies certain AI systems used in education and vocational training as high-risk, including those used to evaluate learning outcomes or determine access to education. The requirements that apply to an AI tool in corporate e-learning depend on its intended purpose and use. Before implementation, we therefore assess what the AI system will be used for, what data it will process and which decisions require human oversight. This helps us identify applicable regulatory obligations and plan appropriate security measures and content review procedures. We discuss these ethical considerations in more detail in our company blog article on AI ethics in education. The future of AI in education: making corporate learning effective Artificial intelligence can significantly streamline corporate training development, particularly when used in tools designed specifically for e-learning. AI4E-learning, for example, helps structure courses, automate repetitive tasks and create exercises. A subject matter expert remains responsible for factual accuracy and the quality of the final course. Using general-purpose language models in training requires careful content review and oversight of the learning process. AI can generate inaccurate information, and access to ready-made answers does not necessarily help employees retain knowledge or develop skills. A well-designed training programme should therefore encourage employees to solve problems independently and apply what they have learnt in practical situations. Where to start? Choose one repetitive training process, define the rules for expert content verification and check whether employees can independently apply the acquired knowledge. If you are planning to use AI in corporate training, contact our specialists. During a free consultation, we will discuss your needs and the possibilities of implementing AI4E-learning in your organisation. TTMS Malaysia is a Registered Training Provider with HRD Corp, so Malaysian employers can fund TTMS training from their HRD Corp levy. FAQ – Frequently asked questions How is AI changing education and corporate training? AI can be used to create courses faster, personalise learning paths, generate exercises and feedback, and translate content into multiple languages. The final result is always verified by an expert or trainer. Will AI replace trainers or teachers? No. AI supports the trainer by taking over repetitive work and personalising learning, while decisions regarding scope, quality and context remain in human hands. How does generative AI in education speed up course creation? Tools such as AI4E-learning generate a structured course draft from source materials. A subject matter expert reviews and refines the content before the approved course is exported as a SCORM-compliant package. This can significantly reduce development time, while expert review remains essential to ensuring quality. What are the risks of artificial intelligence in learning? The main risks include inaccurate AI-generated content, inadequate protection of personal data and barriers to accessing training. Certain AI systems used in education may also be subject to high-risk requirements under the EU AI Act, depending on their intended purpose and use. These risks can be reduced through expert review, appropriate controls over data access and processing, and assessment of applicable legal requirements. Does using AI impair knowledge retention? The studies discussed above suggest that relying on AI-generated answers may reduce engagement in critical thinking and affect performance when AI support is removed. The findings vary by study design and context. Training should therefore include tasks that require learners to recall information and solve problems independently, alongside expert review of the course content.
Read
Case study: How we improved a RAG chatbot for exam candidates
How can you help customers find a specific answer in hundreds of pages of documentation? An education company we work with planned to give its customers access to a chatbot that could answer questions about exam procedures. Before making the tool more widely available, the quality of its answers needed to improve. The TTMS team refined how the chatbot used the documents, increasing answer accuracy from around 70% to around 98% in an internal test. We prepared this case study using an internal presentation and project information shared by Jakub Kraśniewski, Senior AI Developer at TTMS. About the client: an education company supporting exam candidates Our client operates in the education sector and supports people preparing for a certification exam. Candidates need information at different stages, including registration, exam procedures, receiving results and appealing a grade. The company provided this information in PDF documents totalling several hundred pages, mainly in English. Finding the right answer therefore required customers to search through extensive materials themselves. The chatbot was intended to help them handle exam-related matters and reduce the support team’s workload. The challenge: improve answers before releasing the chatbot to customers Candidates needed to be able to describe their situation in their own words and receive clear guidance within around 4–5 seconds. Answers also needed to be complete. If a procedure applied only under certain conditions, the chatbot needed to explain them. TTMS was responsible for improving information retrieval in the existing solution, which had been built using CrewAI, a framework for developing AI agent-based systems. The chatbot used RAG (Retrieval-Augmented Generation) to generate answers from retrieved passages in the client’s documentation. Our analysis showed that the text chunks supplied to the model were too large, making them harder to match to a question. Text extraction from multi-column PDFs caused another problem: content from adjacent columns was being mixed together. Improving the chatbot therefore required examining what information the model received and whether it preserved the meaning of the source document. Solution and implementation: answers with the necessary context We changed how the documentation was divided into chunks, preserving the connections between sentences, paragraphs and pages. When the system found a sentence relevant to a question, it could also retrieve the surrounding paragraph or the entire page. This gave the model the information needed to explain a rule along with the conditions under which it applied. This approach allowed us to use the client’s existing materials and retain classic RAG. According to Jakub, the additional storage and processing costs were acceptable for this volume of documentation. We evaluated the changes using an internal set of questions covering the full scope of the materials. We also included real user questions collected anonymously during an earlier prototype launch. This helped us assess answers to questions phrased in the way customers actually asked them. We explain the technical approach in our article “RAG for chatbots using CrewAI – notes from a TTMS Tech Talk”. Results: around 98% answer accuracy in an internal test According to the data shared by Jakub Kraśniewski, answer accuracy increased from around 70% to around 98%, an improvement of approximately 28 percentage points. The solution also maintained a fast response time. This result applies to the internal test set prepared for the project. It confirmed the improvement in answer quality and helped prepare the tool for the next stage: release to a subset of customers. The actual reduction in the support team’s workload had not yet been assessed. What comes next? Evaluating the chatbot in everyday candidate support After completing internal testing, the company planned to make the chatbot available to a subset of customers. This stage will help establish whether candidates receive enough assistance to resolve their enquiries and need to contact a support adviser less often. The assessment will draw on chatbot usage data and support enquiries. Let’s talk about a chatbot for your company Would you like to make company documentation easier for customers or employees to use? Or do you already have a chatbot whose answers need improvement? Talk to the TTMS team. We will review your materials and users’ needs to recommend a solution that fits your business. Where should you start with a customer service chatbot project? Start by reviewing support enquiries to identify the questions customers ask repeatedly. Issues for which the company has clear, documented answers are good candidates for the initial scope. Next, define who the chatbot should help and what users should be able to accomplish through a conversation. This makes it easier to set the scope of a pilot and decide how to assess its results. Involve customer service staff early, as they understand common misunderstandings and situations that require an individual decision. A scope prepared this way gives the implementation team a concrete starting point. Can you improve an existing chatbot without rebuilding it from scratch? In many cases, individual components of an existing solution can be improved, although the extent of the changes requires an initial assessment. The team should review examples of incorrect answers and identify where the problem occurs. The cause may lie in document preparation, information retrieval or how the model uses the retrieved content. The limitations of the current platform and access to its configuration also matter. Before deciding to rebuild, it is worth comparing the effects of selected changes using the same set of questions. This helps establish whether further development of the existing tool is justified. What determines the cost of implementing a chatbot that uses company documents? The cost depends partly on the condition of the source materials, the integrations required and the tool’s operating requirements. Documents with complex layouts or inconsistent content may need more preparation. Connecting the chatbot to company systems is a separate task, particularly when access to information depends on user permissions. The budget should also cover testing, support after launch and knowledge base updates. Ongoing costs depend on conversation volumes, the models selected and how questions are processed. An estimate should therefore distinguish between the cost of building the solution and the expected cost of maintaining it. How do you plan a customer chatbot pilot? A pilot should cover a clearly defined range of enquiries and a group of users whose questions will help assess the tool’s usefulness. Before launch, agree on the criteria for expanding access, including expected answer quality, acceptable response times and how errors will be handled. Users must be able to report a problem and contact support. During the pilot, the team should review conversations in line with the organisation’s data protection rules and collect customer feedback. It is important to check whether answers help users resolve their enquiries, including when questions are imprecise. The results help determine what needs to improve before the chatbot reaches a wider audience. How can you assess whether a chatbot actually reduces customer support workload? Use data from before the chatbot’s launch as a baseline: enquiry volumes for selected topics, handling times and how often customers make repeat contact. After implementation, compare the same measures while accounting for seasonality and changes in customer numbers. A user who does not contact an adviser after speaking to the chatbot has not necessarily resolved their issue, so customer feedback also matters. Support may receive fewer straightforward questions, leaving complex cases to account for a larger share of its work. In that situation, the average handling time per enquiry can rise even as the team’s overall workload falls. Considering these measures together provides a more reliable assessment of the business impact.
Read
GPT-6.1 Sol for business: Greater capabilities, lower costs
On 29 September 2026, at DevDay, OpenAI introduced GPT-6.1 Sol, just one week after the launch of GPT-6 Sol. The company aimed to bring Sol closer to GPT-6 Astra’s capabilities in coding, document analysis and application use, while keeping the model’s existing base prices. OpenAI kept GPT-6 Sol’s pricing: USD 2 per million input tokens and USD 10 per million output tokens, one fifth of Astra’s standard rates. OpenAI also links the update to the development of AI agents, programs that complete tasks step by step using available tools. Analysing documentation, preparing a code change and checking that it works may require multiple calls to the model. The cost of this work grows with the number of operations. GPT-6.1 Sol is intended to let application developers tackle more demanding tasks within the same budget. 1. What is GPT-6.1 Sol, and what has changed since GPT-6 Sol? GPT-6.1 Sol builds on GPT-6 Sol and is designed for complex tasks involving code, documents and applications. OpenAI’s documentation also lists support for tools, including search and code execution. The model can be used in an AI agent connected to a company’s data sources and tools. An agent could read a customer enquiry, find the relevant specification, compare requirements and draft a response. The company must define which data the agent can access, which actions it can perform independently and which require an employee’s approval. Base prices for input and output tokens remain the same as for GPT-6 Sol. The rate for reusing cached data, however, falls from USD 0.20 to USD 0.10 per million tokens. Companies using GPT-6 Sol should test both versions on the same tasks and compare the quality of their results, the number of retries and token usage. 2. What do benchmark results tell us about business applications? OpenAI publishes benchmark results covering document analysis and multistep tasks. When comparing results, check the reasoning level used. A higher level allows the model to spend more computation on analysing a task, which may increase token usage. Benchmark Area assessed Result reported by OpenAI GDP.pdf Answering questions based on complex PDF documents. Results close to Astra’s at approximately one fifth of the cost per task. AutomationBench 1.0.6 Multistep tasks in business applications. A lead of 4.8 percentage points over GPT-6 Sol at the medium reasoning level. OSWorld 2.0 Using desktop applications. A score 2.1 percentage points below Astra’s. The cost per task is approximately one seventh of Astra’s. Both models were tested at the maximum reasoning level. Each benchmark assesses different model capabilities, so their results should be considered separately. GDP.pdf, developed by Surge AI, tests whether a model can analyse workplace documents and answer questions about their contents. The model must also read tables, diagrams and footnotes correctly and connect information from different parts of a document. The result therefore shows how it handles materials similar to those reviewed by procurement departments or technical teams. Zapier’s AutomationBench assesses task execution in simulated applications. It checks whether the model actually made the required changes, such as updating the correct record and completing every requested action. This matters for businesses: a model’s claim that it has completed a task should be supported by data saved in the system. OSWorld tests computer use, including actions performed through application interfaces. The result cited by OpenAI includes credit for partial task completion. A high score may therefore mean that the model completed most steps correctly but missed the final one, such as submitting a form. When assessing a model’s suitability for automation, companies should also check how often it completes the entire task. These benchmark results help companies choose use cases for a pilot. Testing the model on their own documents and in the applications they use will show whether it meets their requirements and how much time is needed to check and correct its work. 3. How much does GPT-6.1 Sol cost, and how should you read the pricing table? API usage, which allows an application to access the model, is billed in tokens: units of processed text that often correspond to parts of words. Input includes instructions and supplied materials. Billable output tokens also include reasoning tokens, which are not visible in the response. Rates in USD per million tokens in Standard mode, for requests containing up to 272,000 input tokens: Model Input Cache read Cache write Output GPT-6 Sol 2.00 0.20 2.50 10.00 GPT-6.1 Sol 2.00 0.10 2.50 10.00 GPT-6 Astra 10.00 1.00 12.50 50.00 This comparison covers standard processing. Faster processing modes and requests with more input data have separate rates, and processing in a selected region may incur a surcharge. Caching can reduce the cost of subsequent requests that use the same instructions or documents. Savings depend on how much data can be reused. The total cost of a task includes token usage, caching charges and the tools used. 4. Example: how much could you save on 1,000 tasks per month? Let’s work through an example: a company completes 1,000 tasks per month, each using 20,000 input tokens and 3,000 billable output tokens, including reasoning. We assume identical usage for both models. To keep the calculation clear, we exclude cache reads and writes, tool fees and surcharges. Token usage must be measured in an actual deployment. Monthly cost component GPT-6.1 Sol GPT-6 Astra 20 million input tokens USD 40 USD 200 3 million output tokens USD 30 USD 150 Total token cost USD 70 USD 350 Token savings amount to USD 280 per month. Now let’s add another assumption: an hour of work by the person checking the results costs the company USD 30. If checking Sol’s results took an average of one extra minute per task, monthly labour costs would rise by USD 500. In this example, using Sol would cost the company USD 220 more per month overall than using Astra. If checking Sol’s results takes the same amount of time as checking Astra’s, or less, lower token spending may reduce the total cost of completing a task. The pilot should compare result quality, model costs and the time spent checking outputs. To calculate the cost per successfully completed task, divide the total process costs by the number of tasks completed according to the agreed requirements. The calculation should also include failed attempts, corrections, exception handling and maintenance. Data preparation and system integration costs should be spread over the planned period of use. 5. Which GPT-6.1 Sol use cases are worth testing in your company? A pilot could cover comparing documents and proposals, preparing information for customer service and developing code fixes. 5.1 Comparing technical documents and proposals A procurement department receives proposals containing specifications, parameter tables and service terms. The system could prepare a comparison against an agreed set of requirements. For each value, it should identify the source document and the location where it found the information, and flag any missing data. The test set should include two versions of the same specification, parameters expressed in different units and a qualification stated in a footnote. The reviewer can then check whether the system selected the current version and interpreted the qualifications correctly. The total time needed to prepare and check the comparison should be compared with the time needed to complete the task without AI. 5.2 Preparing customer service information across multiple systems After receiving a sales enquiry, an agent could find the customer’s account history, check the status of previous support tickets and prepare an entry in a customer relationship management (CRM) system. This requires connections to the relevant applications and access to the necessary data. The first stage of deployment could end with proposed changes being presented to an employee. Once approved, the system saves them and checks the result. Tests should include records for different customers with similar names to check whether the agent selects the correct one. The same task should also be assigned again to check whether the agent recognises the existing entry and avoids creating a duplicate. 5.3 Diagnosing bugs and preparing software changes An IT team can compare the models when analysing tickets, reproducing bugs and preparing fixes with tests. Previously resolved tickets, where the cause of the bug and the required software behaviour are known, make useful test cases. The assessment should cover the correctness of the change, test results and the time needed for a developer’s review. It should also check whether the model limited its modifications to the necessary scope. Too many code changes can make the review longer and make it harder to identify which changes fix the reported bug. 6. How can you compare GPT-6.1 Sol with Astra in your own process? OpenAI’s model selection guidance recommends comparing Sol and Astra on the same task. The comparison should cover result quality, completion time and task cost under conditions close to the intended use. Choose a task with a clear completion criterion. This could be comparing all required proposal parameters or preparing a code change that passes specified tests. Build a set of examples from day-to-day work. Include typical cases, incomplete data and known exceptions. Keep the materials used to refine instructions separate from those used to evaluate the final configuration. Ensure comparable conditions. Give the models the same materials, tools and permissions. Record reasoning settings and limits. You can then adjust each model’s settings to meet the same quality requirements. Calculate the full cost and check the result. Measure correctness, retries, system processing time and human review time. Also record cases that require manual completion. Expand use once the agreed conditions are met. Define which results can be used immediately, which require approval and when a case should be referred to a specialist. OpenAI recommends testing AI systems on tasks that reflect day-to-day work and having their results assessed by people with relevant expertise. Tests should be repeated after changes to the model, instructions or data sources. You can also test a division of work between the models. Sol would handle cases where it meets the required quality standard, while Astra would handle selected, more difficult cases. Define in advance when a task should be passed to Astra, for example when Sol misinterprets documents or produces an incorrect response. If required data is missing, it should be supplied before another analysis. The cost of that additional analysis must be included in the calculation. The final division of work will depend on the test results. 7. Let’s discuss automation in your company At TTMS, we help select AI solutions for specific processes and integrate them with business systems. If you are considering GPT-6.1 Sol, contact us. Together, we can identify tasks worth including in a pilot and determine how to assess result quality and the full cost of completing them. Can GPT-6.1 Sol be connected to a company knowledge base? Yes. An application can provide the model with information retrieved from approved company materials. This can be done using retrieval mechanisms described in OpenAI’s documentation. The approach in which a system first retrieves relevant source passages and then uses them to prepare an answer is known as retrieval-augmented generation (RAG). Implementation requires keeping documents up to date, identifying versions and respecting user access permissions. Providing sources helps users check the answers. Performance should also be assessed on questions for which the knowledge base does not contain enough information. Does switching from GPT-6 Sol to GPT-6.1 Sol require changes to the application? The scope of changes depends on how the application is integrated. The team should check the available interfaces, reasoning settings, tool support and response formats. For example, the GPT-6.1 Sol model documentation states that tool use requires the Responses API and that the none reasoning setting is not supported. This may affect applications built for the previous version. After adjusting the configuration, the team should test it against a saved set of tasks, including error handling. It is worth retaining the option to revert to the previous configuration if the new one does not meet requirements. What is GPT-6.1 Sol? GPT-6.1 Sol is an OpenAI model designed for tasks involving code, documents and business applications. It builds on GPT-6 Sol while keeping the same base prices for input and output tokens. It also supports tools, allowing developers to use it in AI agents that retrieve information and perform actions across connected systems. For businesses, its appeal lies in the balance between capability and cost. Its suitability for a particular process should be assessed through tests that measure result quality, token usage and the time needed for human review.
Read
Nearshoring to Poland: The 2026 Guide
Nearshoring to Poland means working with a software development or IT delivery partner located in a nearby European country rather than a distant offshore location. For many organizations, Poland offers a combination of technical expertise, close collaboration, shared working hours, and a business environment aligned with European regulations. As a result, it has become a popular destination for companies looking to scale delivery teams while maintaining effective communication, quality, and operational oversight.
ReadThe world’s largest corporations have trusted us
We hereby declare that Transition Technologies MS provides IT services on time, with high quality and in accordance with the signed agreement. We recommend TTMS as a trustworthy and reliable provider of Salesforce IT services.
TTMS has really helped us thorough the years in the field of configuration and management of protection relays with the use of various technologies. I do confirm, that the services provided by TTMS are implemented in a timely manner, in accordance with the agreement and duly.
Ready to take your business to the next level?
Let’s talk about how TTMS can help.
Michał Trojanowski
Managing Director TTMS Software UK Ltd.