SightLift

Data sources — what each one captures

Where to start for each AI product, what it can and can't report, and what changes once it's connected.

← Back to the dashboard
Data reaches SightLift three ways, and which ones you get depends on the product: a live telemetry feed, a scheduled API sync, or a manual export upload. The one rule that surprises people: live telemetry is forward-only — it starts the day you connect and never backfills. API syncs and uploads are how you get history.

Start here: what are you connecting?

You useIt connects byStart with
Claude Code
Cowork
Live telemetry Connect Claude — or fan out from a collector if another vendor already consumes it
Claude chat
(claude.ai)
Export · Admin / Compliance API Connect Claude
ChatGPT
(Enterprise / Edu)
Compliance Logs API Connecting OpenAI below
Gemini app
(Workspace)
Vault · Admin SDK Connecting Google below
Codex CLI
Gemini CLI
OTLP-capable Not yet — see below. These emit OpenTelemetry, but each uses its own event schema and we only reconstruct one today.
Something else
that speaks OTLP
Live telemetry Talk to us — send a sample and we'll tell you what we can read

Setup guide

Connect Claude to SightLift

Claude Code, Cowork and Chat, pointed straight at SightLift. The exact admin screens with copy-paste configuration.

Read the guide →

Setup guide

Already send OTel elsewhere?

Run one collector as a gateway and fan out, so your existing vendor keeps everything it gets today and SightLift gets its own copy.

Read the guide →

The three connection methods

Independent of vendor, these behave differently in ways worth knowing before you choose:

MethodHistoryCredentialGood for
Live telemetry Forward-only A SightLift ingest key — you paste it into the tool, nothing outbound from us The only way to see agentic tool use, and the only way to see Cowork at all
Scheduled API sync Back to the provider's retention limit A read-only org credential you issue to us (no inference, no write, no billing access) Steady history plus ongoing catch-up, without asking anyone to change a setting
Manual upload Everything in the file None — you hand us the export Backfilling beyond an API's window, or when your org won't allow an outbound key

You can use more than one for the same product, and should: an upload for history plus live telemetry going forward is the most complete picture. Adding a source only ever improves what we can measure — it never downgrades something you already had.

What "live telemetry" means

Live telemetry is OpenTelemetry. Your tool — or your own collector — exports to SightLift's ingest endpoint, authenticated by a per-tenant ingest key. The key is shown once at creation, so copy it then.

Logs:     https://app.sightlift.ai/v1/logs
Traces:   https://app.sightlift.ai/v1/traces
Header:   Authorization: Bearer <your-ingest-key>
Two signals, and both matter. Conversation events arrive as OTLP logs; tool output — the thing that lets SightLift prove an automation reproduces your real results — arrives on traces, as a tool.output span event. A setup that sends only logs works, and silently gives up capability verification. There is no metrics endpoint: /v1/metrics returns 405.

Only OTLP over HTTP is accepted; there is no gRPC ingest. Protocol is http/protobuf or http/json — both work on both paths, so use whichever your tool's configuration screen expects.

Where the key comes from. Generate one under Configuration → Data & sources → Anthropic Claude → your plan → Live telemetry. That tab sits on the Anthropic card rather than somewhere neutral for a real reason, not an arbitrary one — see OTLP from other tools.

How much you enable is how much SightLift can do

This is the part worth understanding whatever you connect. Telemetry carries content in layers, and each layer unlocks a different class of answer:

LayerWhat it enables
Metadata only Spot repeated work, measure adoption, attribute cost. A complete picture of how much.
Prompt text Classify work accurately by topic and outcome — what your team is doing.
Tool inputs Capture the command or script that ran, so repeated deterministic work becomes a candidate automation.
Tool output Let SightLift prove a candidate automation reproduces your real results before offering it back to your team.

Products differ in how they expose these, and in which direction the default points:

What "off" actually looks like. With prompt logging disabled, each user_prompt event still arrives — but its text is the literal string <REDACTED>, so SightLift sees metadata and not what was said. Because live telemetry has no backfill, enabling a layer later does not recover the work that happened while it was off. That cuts the other way too: nothing you never enabled was ever collected.

You don't need any of this to start — with metadata alone SightLift still measures your work and proves capabilities forward as they're used. Turn layers on per team as your security review is comfortable. What we store and who can see it: data access & privacy.

Capability matrix

What each product gives you, by ingestion method:

ProductIngestion methodsWhat you get
claude.ai Export · Admin API · Compliance API Org-wide workspace export on Team; programmatic conversation pull + per-message model attribution via the Admin / Compliance API on Enterprise.
Cowork OTEL only Live telemetry only, forward-only. No export or admin API exists for Cowork — it builds from the day you connect a key.
Claude Code Export · Analytics API · OTEL Historical via export / Analytics API; live, forward-only via OTEL telemetry (same key as Cowork).
OpenAI — ChatGPT Compliance Logs Platform On Enterprise/Edu, the Compliance Logs Platform delivers time-windowed JSONL logs of org-wide conversations, files, and workspace metadata (the conversations-logs system replaced the older stateful route in 2026). No live OTLP path for ChatGPT itself.
OpenAI — Codex OTEL · API The Codex CLI exports OpenTelemetry logs (prompts, tool decisions, MCP usage). OTLP-capable like Claude Code — see the note below on SightLift support.
Google — Gemini app Vault · Admin SDK On Workspace, Vault now covers the Gemini app (retention, litigation hold, search, and XML export of prompts + responses), plus Admin SDK / audit logs. No live OTLP path for the Gemini app.
Google — Gemini CLI OTEL The Gemini CLI exports telemetry via OTLP/gRPC or OTLP/HTTP to any collector. OTLP-capable like Claude Code — see the note below on SightLift support.
OTLP from other tools — where this actually stands. Speaking OTLP is not the same as being readable. The chat apps (ChatGPT, Gemini app) expose no OTLP feed at all, so capture those through the Compliance Logs Platform and Vault respectively. The coding CLIs (OpenAI Codex, Gemini CLI) do emit OTLP — but each one uses its own event names and attributes, and SightLift's reconstruction understands the Claude Code event family only (Claude Code + Cowork). That is why the Live telemetry tab appears on the Anthropic card and not as a generic endpoint: pointing another tool's OTLP at us today would deliver bytes we cannot turn into conversations. Codex and Gemini-CLI adapters are future work. If you want one, tell us which tool and send a sample export — that is what moves it up the list.

Uploads & scheduled sync

Per-provider specifics

Anthropic — ingest keys

One key works for both Cowork and Claude Code. The key identifies your tenant; SightLift splits Cowork from Claude Code downstream by the telemetry's service.name, so sharing a key never muddles the data.

We still recommend a labeled key per surface — e.g. Cowork — prod and Claude Code — CLI. Separate keys let you revoke or rotate one surface without disrupting the other, and give each its own "last activity" stamp.

No manual allowlisting step for Cowork. The Cowork sandbox blocks outbound network calls by default, but the console now adds your endpoint to its egress allowlist automatically when you save, and says so inline under the endpoint field.

OpenAI — ChatGPT Enterprise / Edu

OpenAI Compliance Platform ↗

Google — Gemini in Workspace

Vault API scopes ↗ · Gemini audit via Reporting API ↗

Official documentation

Anthropic

OpenAI

Google

OpenTelemetry