---
id: post/gerardorenteria-blog/15298
type: post
title: "🚩 Evidence Flags: More trust signal, fewer words"
summary: Evidence Flags is a Copilot skill that adds brief labels to claims to distinguish what is backed by evidence, reported by users, or inferred by the model. It helps when explicitly requested via /ef commands to clarify trust levels in responses without cluttering simple questions.
tier: community
language: en
tags:
  - evidence flags
  - copilot skill
  - trust signals
  - claim verification
  - al development
system: copilot
review:
  state: reviewed
  by: opus
  at: "2026-10-07T23:47:06.819Z"
  flags: []
generated:
  at: "2026-10-07T22:42:12.892Z"
  pipeline: 0.2.0
  prompts:
    extract-post: 1
  input_hash: d8804117ba4278e9dab8af0e19bfe5751459d66735d456a74e58e63132e68d3b
evidence:
  - kind: blog
    url: https://gerardorenteria.blog/2026/08/31/%f0%9f%9a%a9-evidence-flags-more-trust-signal-fewer-words/
    title: "🚩 Evidence Flags: More trust signal, fewer words"
    date: "2026-08-31"
    commit: null
    t: null
    quote: null
  - kind: blog
    url: https://gerardorenteria.blog/2026/08/31/%f0%9f%9a%a9-evidence-flags-more-trust-signal-fewer-words/
    title: "🚩 Evidence Flags: More trust signal, fewer words"
    date: "2026-08-31"
    commit: null
    t: null
    quote: Instead of filling a response with qualifiers such as maybe, I think, or it seems, a brief label is added to relevant claims.
  - kind: blog
    url: https://gerardorenteria.blog/2026/08/31/%f0%9f%9a%a9-evidence-flags-more-trust-signal-fewer-words/
    title: "🚩 Evidence Flags: More trust signal, fewer words"
    date: "2026-08-31"
    commit: null
    t: null
    quote: "Supported does not mean absolute truth: it means the claim is supported by evidence the model inspected during that conversation."
links:
  learn: []
  objects: []
  features: []
  topics: []
  localizations: []
  videos: []
  posts: []
  guidelines: []
post_id: "15298"
source_id: gerardorenteria-blog
source_name: Gerardo Renteria
url: https://gerardorenteria.blog/2026/08/31/%f0%9f%9a%a9-evidence-flags-more-trust-signal-fewer-words/
published_at: "2026-08-31T13:27:16.000Z"
author: Gerardo Renteria
full_text: false
words: 1163
quotes:
  - text: Instead of filling a response with qualifiers such as maybe, I think, or it seems, a brief label is added to relevant claims.
    why_it_matters: "Explains the core design principle: using structured labels instead of hedging language makes trust levels explicit and scannable."
  - text: "Supported does not mean absolute truth: it means the claim is supported by evidence the model inspected during that conversation."
    why_it_matters: "Critical boundary on what the skill does: it clarifies context-specific verification, not universal truth."
code_objects_mentioned:
  - other Customer
systems:
  - copilot
  - development
versions_mentioned: []
preview:
  embeddable: true
  frame_url: https://gerardorenteria.blog/2026/08/31/%f0%9f%9a%a9-evidence-flags-more-trust-signal-fewer-words/embed/
  image: https://i0.wp.com/gerardorenteria.blog/wp-content/uploads/2026/08/designer-2.png?fit=1200%2C1200&ssl=1
  image_alt: null
  image_w: 1200
  image_h: 1200
  site_name: Gerardo Rentería Blog
  favicon: https://gerardorenteria.blog/wp-content/uploads/2020/11/cropped-wolficon.jpg?w=32
  probed_at: "2026-10-07T11:50:12.148Z"
---

# 🚩 Evidence Flags: More trust signal, fewer words

[Read the post](https://gerardorenteria.blog/2026/08/31/%f0%9f%9a%a9-evidence-flags-more-trust-signal-fewer-words/) · Gerardo Renteria (Gerardo Renteria) · 2026-08-31 · 1163 words · tier community · reviewed (checked by Opus)

> Evidence Flags is a Copilot skill that adds brief labels to claims to distinguish what is backed by evidence, reported by users, or inferred by the model. It helps when explicitly requested via /ef commands to clarify trust levels in responses without cluttering simple questions.

## Key points

- Uses seven labeled tags across two families: provenance (Supported, Reported, Unchecked) and AI analysis (Inferred, Hypothesis, Forecast, Judgment), plus optional warnings for contested or time-sensitive claims
- Activated only when explicitly requested with /ef commands like /ef on, /ef check, /ef trail, keeping normal conversations unaffected
- Helps distinguish between what Copilot verified in files, what users stated, and what the model deduced, without subjective qualifiers like maybe or seems
- Does not verify truth, assign confidence scores, or replace technical review; Supported means claim is backed by evidence inspected in that conversation only

## Quotes

- "Instead of filling a response with qualifiers such as maybe, I think, or it seems, a brief label is added to relevant claims." (Explains the core design principle: using structured labels instead of hedging language makes trust levels explicit and scannable.)
- "Supported does not mean absolute truth: it means the claim is supported by evidence the model inspected during that conversation." (Critical boundary on what the skill does: it clarifies context-specific verification, not universal truth.)

## AL objects mentioned

As named in the post. A name that matches one object page by exact type and name links to it; the others stay as named.

- other "Customer"

## Context

- Features: Evidence Flags skill, Claim labeling by provenance, AI analysis tagging, Time-sensitive warning, Contested source warning, /ef command interface

Source: Gerardo Renteria, community blog. Summary, key points and quotes are derived (CONTENT-NOTICE.md); read the original for the full text.