Data For Science

Agentic workflows training: tool use, planning, and multi-agent systems

A hands-on workshop for engineering, data, and product teams on agentic workflows: tool use, planning, multi-agent systems with CrewAI, MCP servers from scratch, and containing the ways agents fail. Taught live online, on-site, or blended.

Fig. 1. The sessions on this page by date, over the twelve months around today. Each mark is one session; the dotted line is today.

What it covers

The material comes from courses Bruno already teaches publicly, and from code we have published. A private session takes it and points it at your systems.

  • Tool use
  • Planning
  • Multi-agent systems with CrewAI
  • MCP servers from scratch
  • Containing the ways agents fail

Taught in public

The public sessions on this topic. The private format is the same material, tailored to your team, your stack, and your data.

Upcoming

  1. From Loop to Harness: Building Reliable LLM Agents in Pure Python

    PyData Global

    Bare bones agents are just a short loop around one LLM API call, an approach that breaks fast in practice. Tools receive invalid arguments, context grows without bound, costs spike, and bad outputs ship unchecked. In this hands-on tutorial we will build a complete agentic harness from scratch in pure Python. We include typed tools, parallel plan execution, tiered memory, output verification, and hard budgets, one testable step at a time.

  2. LLMs for Quant Research: Build Text Signals & Research Agents You Can Trust

    Packt, Live on Zoom, 4 hours, $179.99

    A 4-hour hands-on workshop on building LLM research tools for quant finance. Learn to extract features from earnings calls and filings at scale, build a filings Q&A system with citations, and deploy research agents with guardrails. Includes golden datasets, evaluation harness, and production deployment patterns.

Already taught

  1. Gate Your Agent in 100 ms

    Maven, Free lightning lesson, 30 min, Zoom + recording

    Gate 41 proposed agent actions (five of them adversarial) with Jev and Claude against the same written policy. Measure recall on unsafe actions, false-block rate, p95 latency, and cost per million checks — then set the auto / confirm / human bands.

  2. Harness Engineering: Build an AI Data Analyst You Can Actually Trust

    Packt Publishing, Live on Luma, 4 hrs, $149

    Join Bruno Goncalves for a 4-hour, hands-on virtual workshop to engineer a reliable, production-ready AI data analyst in Python. You will connect an agent to permissioned MCP tools, manage context within a hard token budget, build layered guardrails against prompt injection, verify the numbers in an AI report, and make failures diagnosable with retries, budgets and structured traces — ending with a reusable, framework-free Python agent harness. Runs on your laptop: no GPU, cloud account, or API key required.

All events

Formats

  • Live online

    Interactive remote sessions with exercises, live coding, and Q&A — the format Bruno has run for O’Reilly, Pearson, and Packt since 2019.

  • On-site or in-person

    Deep dives tailored to your stack and your use-cases, working with your data where it can be used.

  • Blended

    Pre-work, workshop, and follow-up office hours, so what was learned actually lands in your codebase.

The methods, written up

We publish the code behind the advice. The articles on this topic:

Questions about the training

Who is it for?
Engineering, data, and product teams.
Is it online or in person?
Either. Live online: interactive remote sessions with exercises, live coding, and Q&A. On-site: deep dives tailored to your stack and your use-cases. Blended: pre-work, workshop, and follow-up office hours.
Can it use our stack and our data?
Yes. Private sessions take the material Bruno teaches publicly and point it at your systems; on-site sessions work with your data where it can be used.
What does the team do during the session?
They build. No slideware tours: your team builds a RAG pipeline, an eval harness, or an agent during the session, on patterns they can carry straight into your codebase.
How do we book?
With a call: thirty minutes to pick the topics, the format, and the depth — and leave with a proposed outline.

Tell us what your team needs to ship.

Thirty minutes to pick the topics, the format, and the depth — and leave with a proposed outline.

Discuss training

Or email info@data4sci.com