← back
The Robots are coming for your job, and that's okay - Elmer Thomas and Maria Bermudez
Takeaway
A small team can scale docs work by composing many narrow agents behind a lint-+CI-+human-review pipeline rather than betting on one mega-bot.
Summary
- Twilio's docs team built six single-purpose agents (editor, alt-text, jargon-simplifier, SEO meta, outline-builder, Slack triage) behind a Next.js UI instead of one mega-bot.
- Custom GPT-4o-1 agents pull style guide + rubric from Airtable so non-engineers can iterate; outputs flow through Veil lint + CI/CD + CODEOWNERS review before merge.
- Reduces hallucinations via layered validation: agent → lint → tests → PR review → product/eng review → human merge.
- Three-step playbook: identify one painful workflow, pick one repeatable rule-based task, loop with users weekly to refine.
agentsdocstwilio
Original description
In a world where AI is revolutionizing API documentation, many wonder: “Why can’t we just use AI to write the docs?” At Twilio, we’ve explored this question deeply. Our Developer Education team found that while generative AI is powerful, it still carries too much risk to be used as an autonomous customer-facing agent. Instead, we use AI to amplify our small team’s impact by automating repetitive tasks, freeing us to focus on high-value, accuracy-critical work. This talk shares our journey building and deploying AI agents to streamline documentation workflows, support over 100 product managers, and empower less-technical colleagues to contribute. Attendees will learn practical strategies for integrating agentic AI into documentation processes, how to balance automation with human oversight, and ideas for taking their own docs to the next level. This session is ideal for anyone interested in the intersection of AI, APIs, and documentation, especially those on short-staffed teams seeking scalable solutions.