Engineering brief
Managing AI Like Humans Is the Only Way to Trust It
At a glance
- Relevance
- Practical value
- Warnings
- None
Upside.tech uses a 'jury and judge' workflow where multiple agents independently research and a consensus agent weighs reasoning quality. This builds trust but requires upfront documentation of business logic.
AI agents are being adopted by non-technical teams; without trust scaffolding, they amplify errors instead of productivity.
Summary
The AI trust problem in GTM teams is acute—agents confidently produce wrong answers. The speaker argues the fix isn't better prompts but managing AI like humans: provide commander's intent, documentation, and verification workflows.
Three concrete examples: scaffolding website redesigns with anchor assets and citations; a “radiant librarian” that injects organizational context into queries to prevent naive assumptions; a “jury and judge” workflow where multiple agents independently research and a consensus agent weighs reasoning quality for attribution.
The hidden tradeoff: these patterns require upfront investment in documenting business logic, personas, and data definitions. The payoff is that non-engineers can build trustworthy AI tools without deep technical expertise.
Bonus insight: never trust free or low-tier AI products for critical work—they lack the reasoning power and guardrails needed. Model selection is a governance decision. The talk is light on quantitative evidence but strong on operational pragmatism.
Watch the video
This video is blocked due to your privacy settings. To watch this video, please accept YouTube marketing cookies.
Related breakdowns
Why a Positive A/B Test Is Not Enough for AI Features
Bumble's PM reveals why a positive A/B test for an AI feature is only the start: low adoption, bad long-tail outputs, hidden costs, and regulatory walls.
Why Your AI Agents Need a Manager, Not Just Permissions
AI agents need HR-style governance: identity, sponsor, and machine-speed oversight. The talk from Gravitee offers a framework but no proof.
Model Choice Barely Matters: Fix Engineering Culture, Not AI Tools
AI model choice explains under 1% of developer output variance, per Jellyfish's 50,000-engineer dataset. The levers leaders control matter more.
Get TL;DW
Too Long; Didn't Watch.
A concise breakdowns of the AI and devtools videos that actually matter for engineering leaders.
Free. Weekly. No hype.
Video and thumbnails remain the property of their respective creators. tldw.news provides editorial analysis, commentary, and discovery links to original content.