Multidisciplinary agent review
A workflow in which specialist passes apply distinct methods and produce concrete evidence, rather than merely imitate expert personas.
Describe what the work does for people to identify relevant disciplines. Specify each pass’s method, artifact, scope and handoff.
Run dependent passes sequentially and independent investigations in parallel. Shared acceptance criteria prevent specialists from optimizing incompatible objectives.
Connected
- Altitude, depth and rangeFelix Rieseberg’s framework for ambition with AI models: speed repeats work faster, altitude targets outcomes, depth uses expert instruments and range combines disciplines.
- Claude Code subagentsSpecialised agents with their own instructions, tools and context window that the main Claude Code session can delegate tasks to.
- AI outside judgeAn acceptance check outside an agent’s self-assessment, such as a deterministic test, held-out evaluation, measurement or separately briefed reviewer.
- Accessibility testingEvaluation of digital accessibility through automated checks, knowledgeable manual assessment and research with people with different access needs. Conformance evaluation and usability research provide complementary evidence.
Field notes that cover Multidisciplinary agent review
More concepts & methods
- machine learningscientific study of algorithms and statistical models that computer systems use to perform tasks without explicit instructions
- deep learningspecialized form of machine learning that uses artificial neural networks to identify patterns in data
- genetic algorithmcompetitive algorithm for searching a problem space
- Outcome-based promptingAsking an AI agent to pursue a specified change for a user or system, with evidence and boundaries, instead of merely producing a named deliverable.
- Prompt injectionAn attempt to make an AI system follow instructions embedded in untrusted material such as email, documents or websites instead of the authorized user’s task.
- AI data retentionThe rules governing which AI inputs, outputs, logs and derived records remain in a system, for what purpose, and for how long. Not using data for training does not mean that it is not stored.