← All articles How it works

Governing prompts and agents: from a certified prompt to an auditable action

How Insight Prompts and Insight Lense split the job of AI governance: prompts are authored, tested, approved and versioned in one place; every run, authority decision and business change is traced in the other.

Once an AI system answers customers or changes records, two questions follow every incident: what instructions was it running? and what exactly did it do? In the Insight suite, those are two products. Insight Prompts governs the instructions; Insight Lense keeps the evidence.

Prompts as governed assets

In Insight Prompts, a prompt moves through four stages in one registry:

  1. Create: business-friendly authoring with reusable templates, variables, partials and few-shot examples.
  2. Test: run the prompt against curated datasets and have an LLM judge score the output against a rubric you wrote.
  3. Approve: multi-stage workflows with role-aware sign-off from owners, compliance and security.
  4. Deploy and monitor: applications pull certified prompts through the API or SDKs (Python, Node, Java), with per-prompt scorecards for latency, cost, judge scores and feedback.

Every prompt is versioned, diffable and can be rolled back. A new version can run as a challenger on a slice of live traffic and be promoted only if it beats the current one on the rubric.

Evidence, not just logs

A log of model calls says which model ran and what it cost. Insight Lense is built for the moment an agent can change a record, and keeps three kinds of evidence as one thread:

  • The run: every step the agent took, in order, as parent and child spans grouped into sessions, with tokens, latency and cost on each.
  • The authority decision: what the agent asked to do, what it was permitted to do, and who it had to ask. A refusal is recorded as a result, not an error.
  • The business event: what actually changed, as an append-only record with old and new values, the kind of actor and the reason.

Around those sit cost and budgets derived from traces, alerts on failure rate, spend, latency and escalation, and a single score primitive for any judgement. Lense ingests standard OpenTelemetry (OTLP) and has a Python SDK with automatic instrumentation for Bedrock, OpenAI and Anthropic.

Testing the application, too

Prompts and traces govern the AI parts. Insight Test Bench covers the application around them: an AI-native QA platform that crawls every page, generates grounded test cases, runs them nightly and files pull requests.

Example · a made-up claims team

Why did the agent set that reserve?

At a made-up specialty insurer, a claims agent raises a reserve from $50,000 to $250,000. A supervisor asks why. In Lense, one query on the claim returns the thread: the documents the agent read, the reasoning steps, the authority check (raising a reserve above $100,000 needed a human approver, who approved it), and the business event with old and new values. The trace also names the prompt version, v12, approved in Prompts two weeks earlier after beating v11 on the claims rubric.

Governance is a practice. These products record and enforce what you define: rubrics, approval steps, authority levels, retention. Deciding those, and reviewing them, is still your team's job, and regulatory expectations for AI vary by industry and region.

Five questions the records should answer

The Lense site frames observability by the questions people actually ask, each answerable with one query:

  • An auditor: "Everything that happened to this account, in order."
  • A supervisor: "Why did the agent settle at that number, and what was it refused?"
  • Compliance: "Which actions were taken by agents rather than people this quarter?"
  • Operations: "Did that event reach the next system, and how late?"
  • Finance: "What did it cost to handle this piece of work?"

A useful exercise before any agent goes live is to write these five questions for your own process and check that the traces you're collecting can answer them.

Related: the reference architecture.

See the right Insight products in your environment

Tell us what you're trying to build, and we'll walk you through the products that fit, with your data, where it lives.

Request a demo

Keep reading

Guide
Ask + RAG + LenseCatalog + PromptsDLM

Guide: a phased adoption plan for the Insight platform

Where to start and what to add next: a first phase with Ask, RAG and Lense, a second with Catalog and Prompts, and a third with domain models and domain solutions, with the questions that decide when to move on.

November 17, 2026 · 8 min read
Use case
Insight CatalogAutomation HubInsightKafkaInsight Dataflow

Use case: moving a data platform without losing track of what depends on what

A made-up retailer's data team migrates warehouses and Kafka clusters with Insight Catalog for lineage and impact analysis, Insight Automation Hub for validated migration runs, InsightKafka for cluster health, and Insight Dataflow for the new pipelines.

November 15, 2026 · 8 min read
Use case
Insight AskInsight RAGInsight Lense

Use case: one search box for IT operations, across tickets, wikis and code

How a made-up manufacturer's IT operations team uses Insight Ask on top of Insight RAG: connect ServiceNow, Confluence, Jira, Slack and Git, keep permissions intact, and trace every answer with Insight Lense.

November 13, 2026 · 7 min read