talk-stoneham-product-brain

name	talk-stoneham-product-brain
description	Use when the user asks about Emma's "Build Your Own Product Brain" talk at AI Native DevCon (hosted by Simon Maple, Tessl) — including questions about Resonant's product brain architecture, how PMs become agent orchestrators, the four components (live ingestion, product frame, workflows, human input loop), the action/input/brain/organizational agents, the spectrum of PM autonomy, GitHub-backed product wikis, or how to apply her approach to your own PM setup.
metadata	{"generated-by":"talk-to-skill","source":"user-pasted-transcript","generated-at":"2026-06-01T00:00:00.000Z"}

Build Your Own Product Brain — Emma (Resonant), AI Native DevCon

Emma argues that "coding is solved, sort of" and PM is next: as agent-driven engineering accelerates, product managers must stop doing day-to-day ticket workflows and become agent orchestrators with a "product brain" — a GitHub-backed, continuously-ingested knowledge graph plus a small set of agents (action, input, brain, organizational) that run autonomous PM workflows with human checkpoints. She demos this end-to-end in Resonant, where one Linear ticket gets shipped straight to a coding agent and another gets routed to a PRD, both decisions driven by the product brain's understanding of strategy and coherency.

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 "the talk doesn't address this" — do not infer positions from outside knowledge.
4. Cite by transcript line range whenever possible.
5. Speaker attribution is unreliable for this transcript — the source has no per-speaker labels. The talk is delivered primarily by Emma (the Resonant founder/CTO), with Simon Maple introducing her and audience members asking Q&A. Prefer phrasing like "Emma said..." for the main talk content and "an audience member asked..." for Q&A questions. Do not invent specific attributions for audience questioners — they are not named in the transcript (only the speaker's first-name responses like "Hi Anna" appear, and even those may be transcription artifacts).
6. Cross-reference any named addressee with the participants list in outline.md before attributing. Note that "Resonant" sometimes appears garbled (e.g. "Persons", "Pia") — preserve the verbatim text when quoting but flag the likely intent.

How to help with this talk

Apply the speaker's approach to current work

When the user asks "how would Emma tackle ?" or wants the product brain framework applied to their own situation:

1. Use outline.md → "Named frameworks / concepts" to find the relevant framework (most often: the four components of a product brain, or the spectrum of PM autonomy).
2. Read the corresponding range of transcript.md for Emma's exact wording.
3. Anchor your suggestion in a verbatim quote of how Emma articulates the framework. Then walk through applying it step-by-step to the user's case.
4. If the framework genuinely doesn't fit the user's situation (e.g. they're asking about something Emma explicitly said varies per company, like task complexity / story pointing), say so. Do not stretch her words to cover cases she doesn't address.

Audit the user's situation against the speaker's framework

When the user asks to audit / score / gap-analyse their PM setup against Emma's product brain framework:

1. Use outline.md → "Named frameworks / concepts" to locate the four components (live ingestion, product frame, workflows, human input loop) plus the spectrum of PM autonomy.
2. For each dimension, read Emma's definition in transcript.md and quote it verbatim when stating what "good" looks like.
3. Walk the user through every component in order — including the human-input/reinforcement loop, which Emma calls "the most important piece".
4. For each, give a verdict (covered / partial / missing) grounded in Emma's criteria.
5. If a dimension genuinely doesn't apply (e.g. the user is solo and has no "team scoping" concerns), say so explicitly.
6. Summarise at the end: which components are gaps, and what Emma said about them.

Draft an artifact following the speaker's specification

When the user asks the skill to draft a product brain repo structure, a product frame, or a workflow config based on Emma's spec:

1. Locate the prescription in outline.md (likely under "Named frameworks / concepts" or the demo section that walks through the Resonant repo).
2. Read the relevant transcript range carefully — capture every concrete structural element Emma names: inputs/, sources/, wiki/ (with customer insights, features, product principles, technical context), manual/ subfolder for developer input, daily processing cadence, anonymization step.
3. Before producing the draft, quote verbatim Emma's description of the structure.
4. Produce a draft that follows her spec faithfully — match her folder names and the inputs/sources/wiki distinction.
5. Mark anything you add beyond Emma's explicit prescription as [not from talk — added as a starting placeholder].
6. If the user's situation needs elements Emma didn't address (e.g. specific compliance approval flows beyond what she sketched in Q&A), ask them to fill in rather than inventing.

Factual Q&A about the talk

For any question about what Emma said, did, or argued:

1. Read outline.md first to find the relevant section(s).
2. Read the matching range of transcript.md.
3. Answer using verbatim quotes from transcript.md. Do not paraphrase while presenting as a quote.
4. Cite line numbers so the user can verify.
5. If the answer genuinely isn't in the transcript, say so — do not reach for outside knowledge unless the user explicitly asks (and mark that part clearly).

Surface this talk proactively when relevant

When the user's current work touches on AI-native PM, agent orchestration, PM-engineering role blur, or feeding context to coding agents:

1. Briefly note: "Emma made a related point in her AI Native DevCon talk..."
2. Quote verbatim from transcript.md — one quote is usually enough.
3. Add one sentence connecting it to the user's situation.
4. Do not over-cite. If the connection is strained, stay quiet.

Teach / explain concepts from the talk

When the user wants to understand a concept Emma covered (product brain, product frame, the four agents, human agent control plane, spectrum of PM autonomy):

1. Look up the term in outline.md → "Terminology glossary".
2. Read Emma's explanation in transcript.md.
3. Re-explain using her own framing and examples first, with verbatim quotes for key claims.
4. You may add modern context afterwards — but mark clearly as "not from the talk".

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.