corteX Lens iconcorteX Lens
  • Home
Sign inSign up
corteX Lens iconcorteX Lens
corteX Lens iconcorteX Lens

Your workspace is waiting on a wider screen

Lens lays out a lot of signal at once, so it is built for the desktop. Open it on a laptop or a larger display and everything will be right where you left it.

Loading this view

corteX Lens iconcorteX Lens
  • Home
Sign inSign up
corteX Lens iconcorteX Lens

Loading this view

corteX Lens iconcorteX Lens

Your workspace is waiting on a wider screen

Lens lays out a lot of signal at once, so it is built for the desktop. Open it on a laptop or a larger display and everything will be right where you left it.

Understand and govern every AI engineering workflow

Lens brings activity, project and developer cost, source coverage, anomalies, policies, approvals, and the evidence behind each decision into one operating view. Start with one source and follow each material change from evidence to an accountable decision.

See the work. Understand the change. Govern the response.

One time window and scope follow every step, so the evidence you notice on Home is the evidence you investigate, discuss, approve, and audit.

01Observe the work and its costSee AI activity and reported cost by project, team, developer, model, tool, capture source, and provider. Compare periods and see which evidence is priced, estimated, or missing.Explore Observability02Explain what changed
Open a material anomaly to inspect its baseline, movement, cross-dimension contributors, source coverage, and underlying sessions before deciding what it means.
Inspect anomalies
03Make one accountable decisionPromote an anomaly or request into one owned case with a due date, comments, approval history, and immutable source evidence instead of a stream of disconnected tickets.Open Decisions
04Govern the responseCreate and simulate policies, route approvals and exceptions, inspect enforcement evidence, and preserve real-actor attribution even while using View as.Open Policies
Ask Lens stays in the same contextAsk about the selected evidence, compare roles or people below you, and receive an explanation that distinguishes observation, inference, and a proposed action.Open Ask Lens

Connect your stream

Start with one read-only source. Lens turns the first real signal into cost, activity, anomaly, policy, and source-coverage evidence.

Optional optimization, after observability and governance

Teams that opt in can also find removable prompt residue and verify measured savings without making token reduction the product's operating model.

Explore the optional benchmark and session demoOpen proof

30-second demo

Inspect one AI coding session

Paste one log to see the evidence Lens extracts and the optional token-removal opportunity it can identify on this sample (). No install, no account, no data retained.

see the live catalog

The comparison above runs one prompt. To run the full benchmark, the playground replays a full dataset and compares savings and parity across model and toolset configurations. Open the playground.

Ready to see and govern your AI operations?

Start a free pilotSign in

Sample data lives entirely in your browser.

Public benchmark proof

Live numbers from the real developer transcripts replay

Published June 18, 2026.

Median savings

25.3%

input-token reduction per session, combined across 1 dataset

Quality

No regression detected

26.2% parity, p=0.21

the share of replayed pairs the judge scored at full parity with the baseline

Sample size

42replayed pairs in this run

each pair runs the same prompt with and without lens optimization

No regression detected is the honest read here. The parity figure is the share of replayed pairs the judge scored at full parity with the baseline, and at this sample size the difference from baseline is not statistically significant (Wilcoxon p=0.21). A non-significant difference is not proof of equivalence, so the measured story is no regression detected while the savings land, not a quality regression and not proven parity.

View the published numbers | View run history | Read the methodology