One- and two-day workshops on your codebase, in your hours, by the engineers who ship agents for clients. Your team leaves with a configured repo, not a slide deck.
We review your repo, stack and goals in advance.
Mental model, instructions, permissions, test-driven prompting.
Hooks, skills, subagents, Agent SDK, evals.
Six weeks of support and a metrics review.
| Tier | Scope | Timeline | Price |
|---|---|---|---|
| Half-day briefing | Leadership + tech leads | 1 session | $1.5k – $3k |
| Two-day workshop | Up to 20 engineers | 2 days + 6 weeks support | $6k – $12k |
| Rollout programme | 20–200 engineers, metrics | 6–10 weeks | From $18k |
Every project starts with a written scope and a fixed price, delivered within 48 hours of your brief.
Both. Most are remote; on-site in India and on request elsewhere.
Claude Code and the Claude Agent SDK in depth, MCP, and the evaluation practices that apply to any model.
No — we split tracks by experience in larger teams.
How to roll out Claude Code across an engineering team without chaos: repo conventions, permissions, hooks, shared skills, metrics — and the training we run.
What the Claude Agent SDK is (Claude Code as a library), what it gives you out of the box, when to use it over the plain API, and how we ship agents on it.
An agent harness is the loop, context management, tools and guardrails around the model. What it contains, why most agent failures live there, how we build one.
We reply within 24 hours at hello@truecodeai.com with how we would build it.