/autonomous-investigation

name: autonomous-investigation
description: "The protocol behind every investigation skill. Use when AI research must proceed without you: search-plan gate, Fact/Inference/Assumption labels, confidence stacking, diffable outputs."
intent: >-
  Provide the canonical contract for autonomous research skills: a bounded question budget, a search-plan
  gate, three-level evidence labeling, do-not-invent lists, just-enough output, stable diffable schemas,
  and confidence stacking — so investigations are trustworthy, schedulable, and comparable run over run.
type: workflow
theme: market-intelligence
best_for:
  - "Defining consistent behavior for research skills that run as agent tasks or on schedules"
  - "Keeping AI research honest: labeled evidence, real citations, no invented facts"
  - "Making run N and run N+1 diffable so delta monitoring is possible"
scenarios:
  - "Set up a competitive scan that can re-run quarterly without me babysitting it"
  - "I want research output where I can tell facts from the AI's guesses"
estimated_time: "protocol reference; investigations vary (15-45 min per run)"

Autonomous Investigation Protocol

Purpose

Provide the canonical contract for **investigation skills** — research the AI performs in the world (web search, published data, public filings) while you review the evidence instead of feeding it context. Where `workshop-facilitation` governs skills that ask you questions one at a time, this protocol governs skills that *proceed without you*: they budget their questions, show their plan, label every claim, and produce output stable enough to diff against last quarter's run. That last property is the payoff — an investigation honoring this contract can run as an agent task, in a loop, or on a schedule.

Input

**Nothing required** — this skill defines the protocol other investigation skills follow. **Also useful when invoked standalone:** the target of the investigation and, above all, **the decision the research should support**. Research without a decision is a hobby; every investigation skill asks for the decision because it determines what "just enough" means.

Anything supplied with the invocation itself — text after the skill name, a pasted context dump, or an appended `ARGUMENTS:` line — counts as answers already given. Use it, credit it against the question budget, and don't re-ask.

**Arriving empty-handed? That works too.** The protocol's whole design is to proceed on best-available evidence with labeled assumptions when nobody answers questions. When another skill references this protocol, that skill's Input section governs what to provide.

**Example invocation:** `Run an autonomous investigation on [TARGET]'s move into workflow automation — this supports our Q3 roadmap bet on the same space.`

Key Concepts

Two protocols, two jobs

| | `workshop-facilitation` | `autonomous-investigation` | |---|---|---| | Who holds the context | The user | The world (public sources) | | Interaction shape | One question per turn | Question budget, then proceed | | Blocked by silence? | Yes — waits for answers | No — labels assumptions and continues | | Schedulable? | No | Yes — that's the point |

The contract

Every investigation skill honors all seven clauses. They are not a menu.

1. **Question budget** — a hard cap (usually 3) on clarifying questions. When the budget is spent or nobody answers, proceed with labeled assumptions. This is what makes investigations schedulable: an unattended run degrades gracefully instead of stalling.

2. **Search-plan gate** — before researching, show a 3-bullet plan: what you'll search, which source types, how you'll separate fact from inference. Continue unless the user revises it. *Why it teaches:* reviewing a plan takes 10 seconds; reviewing a wrong report takes 10 minutes. The gate is the cheapest correction point in the whole workflow.

3. **Evidence labels** — every key claim carries exactly one label:

• **Fact** — source-supported; a checkable URL sits next to it
• **Inference** — evidence-based interpretation; the evidence is cited, the leap is yours to judge
• **Assumption** — working guess made to keep moving; listed for validation

Keep labels short. Things you *couldn't find* are not a fourth label — they go in an explicit gaps list. *Why it teaches:* most competitive "facts" in strategy decks are unlabeled inference. Three-level honesty is the habit that separates intelligence from confident storytelling.

4. **Do-not-invent list** — each investigation skill names its domain's specific fabrication risks (competitors, pricing, market share, patent contents, customer wins...) and forbids inventing them. Real, checkable URLs only; a claim without a source and date is an opinion wearing a badge. *Why it teaches:* the list tells the human exactly what to verify first.

5. **Just Enough Mode** — default output is the strongest findings in short bullets, sized to the decision. Verbose Mode exists only on request. Research value is decision support, not page count.

6. **Stable output schema** — section order and structure never drift between runs, so run N and run N+1 are diffable. Delta monitoring, scheduled refreshes, and "what changed since last quarter" all depend on this clause.

7. **Final Step block** — end with exactly 4 numbered next options (artifacts to build, deeper passes to run, assumptions to validate). Accept `1`, `1 and 3`, `Verbose Mode`, or a custom path.

The Confidence Stacking Rule

Labels grade individual claims; stacking grades the *story*. When signals arrive from independent collection channels (see `intelligence-collection-disciplines`):

~~~ 1 channel flags it → Watch item. Log it, do nothing. 2 channels agree → Working hypothesis. Assign someone to probe. 3+ channels agree → Actionable intelligence. Brief leadership, adjust plans. Channels conflict → The most interesting case. Someone is bluffin