CtrlK
BlogDocsLog inGet started
Tessl Logo

talk-batey-building-product-teams-age-of-ai

Use when the user asks about Christopher Batey's talk 'Building Product Teams in the Age of AI: What We Had to Relearn Every Quarter' (Latent Space, 2026) — including questions about running AI-assisted product engineering teams, his three pillars (path to production at AI speed, training/evaluating AI-enabled engineers, designing workflow for parallel change), ADR-first workflows with agents, why review becomes the bottleneck, the producer 'black box' (harness/host/model), vanity metrics vs adoption, two-to-four-person sub-streams, one-complex-task-at-a-time, 'you build it, you run it, you drive adoption', or applying his approach to current work.

78

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Building Product Teams in the Age of AI: What We Had to Relearn Every Quarter — Christopher Batey

Christopher Batey (CTO, Core Engineering Consulting Group) argues that AI is an amplifier — it accelerates building but exposes weaknesses in product decisions, adoption, system understanding, and review capacity. The response is disciplined practice: write ADRs first, keep teams small with adoption-bound missions, work in parallel but only one complex task at a time, and measure adoption — not commits, PRs, or tokens.

Grounding rules — MUST follow when answering

  1. Before answering any specific question, read outline.md to locate the relevant section, then read that section of transcript.md.
  2. When attributing words, quote verbatim from transcript.md. Never put quotation marks around paraphrased content.
  3. If a claim isn't in transcript.md, say so explicitly — do not speculate, extrapolate, or fill the gap with general knowledge. Respond with something like: "Batey doesn't address that in this talk."

Bundle file structure

This skill relies on two supporting files in the same bundle:

  • outline.md — A structured index of the talk's sections and timestamps, used to navigate to the relevant portion of the transcript before answering.
  • transcript.md — The full verbatim transcript of the talk, used as the sole authoritative source for quotes and claims.

If either file is unavailable, state this limitation and answer only from the summary in this skill file, clearly flagging that you are not quoting the transcript.

Example: question and expected output format

User question: Why does Batey say review becomes the bottleneck?

Workflow:

  1. Open outline.md, find the section on review bottlenecks.
  2. Read that section of transcript.md.
  3. Answer using a verbatim quote to anchor the claim, then explain context:

Batey explains this directly: "[verbatim quote from transcript.md]" He argues that AI raises the rate of production while human review capacity stays flat, so the constraint shifts from writing code to evaluating it.

If the transcript does not contain a direct quote on this point, paraphrase without quotation marks and note: "Batey addresses this in the [section name] section, though no single sentence captures it cleanly."

Key quotes

quotes.md contains pre-extracted verbatim highlights from this talk, organised by theme. When formulating answers, check quotes.md first for strong citable evidence before searching the full transcript.md.

Repository
AINativeDev/aidevcon-2026-ldn
Last updated
First committed

Also appears in

jscraik/Agent-Skills
Modified

on Aug 28, 2026

ainativedev/latest-aidevcon-speakers-london-2026
In sync

since Jun 18, 2026

ainativedev/aidevcon-2026-ldn
In sync

since Jun 4, 2026

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.