Intermediate · 1 day
From Chatbot to Agent
A one-day workshop that starts with a basic LLM chat application and evolves it, step by step, into a useful agentic system with retrieval, tools, state and production safeguards.
1 day · Intermediate · Workshops · Developers and technical teams
Overview
Many teams already have a chatbot. The question is how to grow it without rewriting it every time a new capability appears. This workshop uses that progression as the course: chat, structured output, retrieval, tool use, workflow state, agentic behaviour, evaluation and production safeguards.
Each step is implemented on the same application. You see what breaks when structured output is added, what retrieval changes, and why an agent loop is a different system from a chat with extra prompts. The day is a sequence of working increments, not a set of optional extras.
The teaching is deliberately conservative. Not every chatbot should become an agent. The workshop makes the cost of each step visible so your team can stop at the right layer.
You leave with an evolved application and a map of the increments you would take on your own system.
Audience
Developers and technical teams who already have, or are about to build, a chat interface and need a controlled path toward retrieval and agents.
Prerequisites
Ability to work in an application codebase. Prior LLM API experience is expected. A simple chat starter is provided if teams do not bring their own.
Duration
1 day
Can be delivered against your team’s existing chat application where that is practical.
Learning outcomes
- 01
Implement structured outputs on top of a basic chat application.
- 02
Add retrieval without turning the chat into an ungrounded knowledge claim.
- 03
Introduce tool use and workflow state as explicit application capabilities.
- 04
Add bounded agentic behaviour only where the task requires it.
- 05
Evaluate the system at each increment and add production safeguards.
- 06
Decide where your own product should stop on the path from chatbot to agent.
Outline
- 01
Chat and structure
- Basic LLM chat: messages, system prompts, and the limits of free text.
- Structured output as a contract with the rest of the application.
- Build: evolve the starter from chat to structured responses.
- 02
Retrieval and tools
- Retrieval: grounding, citations and refusal.
- Tool use: schemas, side effects and displaying tool activity to the user.
- Build: add retrieval, then one tool, on the same application.
- 03
State, agency and safeguards
- Workflow state versus a hidden agent loop.
- Agentic behaviour with a budget and a stop condition.
- Evaluation and production safeguards: logging, permissions, fallbacks.
- Build: complete the progression and compare each increment on the same tasks.
Practical work
One application is evolved through the eight-step progression. You run the same tasks after each increment so the group can see what improved, what became slower, and which safeguards became mandatory.
Takeaways
- An evolved application from chat through retrieval and tools to a bounded agent
- A step-by-step increment map for the team’s own product
- Evaluation tasks reused across increments
- A production-safeguard checklist for the layer you choose to ship
Delivery
Cognitecta delivers private corporate training, on-site or as remote live training. Courses can be run as published, or adapted to your organisation’s stack, domain and experience level.
Instructor
Nicholas Johnson, AI architect and software engineer. He has a degree in Artificial Intelligence and around twenty years of professional technology training, including hundreds of courses for engineering teams and large organisations. About.
Related courses
1 day · Intermediate
RAG in a Day
A focused workshop for developers: build a complete retrieval-augmented generation system in one day, from ingestion and chunking through citations and a first evaluation.
1 day · Intermediate
Build an AI Agent in a Day
A hands-on workshop for developers: build a working agent with tool calling, state, structured outputs, error handling, permissions and a first evaluation.
1 day · Leadership
AI Architecture Workshop
A facilitated workshop for technical teams, architects and engineering leaders around a real customer problem. The output is an architecture and a next-step roadmap, not a training certificate.