BetaInficy is currently in beta. New account sign-ups are not open yet while we onboard pilot workspaces.
InficyInficy

AI agent execution evidence

See what your AI agents did.Keep evidence you can verify.

Inficy turns captured AI-agent runs into readable, tamper-evident execution records. Inspect recorded steps, tool calls, failures, handoffs and human interventions, export the original NexArt evidence bundle, and optionally certify eligible runtime-observed executions.

Runtime-observed evidence · Agent-reported ChatGPT sessions clearly separated · Optional certification

Your model-provider keys stay in your runtime. Inficy captures execution evidence through supported connectors without proxying your OpenAI, Anthropic or xAI traffic.

Example execution · Illustrative example data, not live customer activity

example-research-agent

EXAMPLE-RUN-001

Completed after recovery

wall clock 4m 08s

Activity time
2m 51s
Actions
18
Human input
1
  1. Read 3 supplier websitesweb · 3 domains · 41s
  2. Called search.querytool · 4 calls · 6.2s
  3. Handed off to pricing-agentdelegation · returned in 22s
  4. Extraction failedparser error · retried once
  5. Operator answered a questionhuman · 1m 12s wait
  6. Renewal quote draftedoutcome: completed · exported
✓ Bundle integrity verifiedCertify execution(optional)
Understand

Your agents work out of sight. Inficy keeps what the capture integration observed.

01

Where it went

Tools, services, models and websites recorded by the capture integration, shown in execution order.

02

How long it took

Wall-clock duration for the run, and a separate breakdown of where the activity time went.

03

What happened

Completions, failures, interruptions, retries, recoveries and every point a human stepped in.

Dashboard

See where agent activity went

Inficy projects readable timelines and analytics from the stored execution evidence. The original NexArt Project Bundle remains authoritative. Wall-clock duration stays separate from recorded activity time, and activity the capture integration did not observe is never invented.

Runtime-observed dashboard metrics are kept separate from agent-reported ChatGPT session analytics.

Illustrative example data, not live customer activity

Execution activity

Runs recorded in the last 7 days

Executions
0
Actions recorded
0
Agents reporting
0

Time by activity

Activity duration, separate from wall clock

Tool calls
0%
Model calls
0%
Waiting on humans
0%
Web and retrieval
0%

Tools and services

What the capture integration recorded

accounting.invoices
0 calls
crm.contacts
0 calls
mailer.send
0 calls

Websites and domains

Hosts reached during execution

docs.supplier.com
0 requests
api.exchange.io
0 requests
status.provider.net
0 requests

Financial activity

States as observed, never assumed

Requested
0
Approved
0
Succeeded
0
Failed / refunded
0 / 1

Human interaction

Where a person entered the loop

Approvals granted
0
Approvals declined
0
Median wait
0m 34s

Handoffs

Work passed between agents

Agent to agent
0
Agent to human
0
Returned incomplete
0

Failures and recovery

Kept in place, never filtered out

Failed actions
0
Recovered by retry
0
Interrupted runs
0

Outcomes

How executions ended

Completed
0
Completed after recovery
0
Failed or interrupted
0
Inspect

Open any execution and read it like a story

Ordered actions
Every recorded step with its timestamp, type, duration and outcome, shown in sequence.
Failures in place
Errors and interruptions stay in the timeline instead of being filtered out.
Human interventions
Approvals, declines and manual retries marked where they happened.
Financial activity
Payment states exactly as observed: requested, attempted, approved, succeeded, failed or refunded.
Trustworthy by default

Tamper-evident evidence, not a mutable activity log

Tamper-evident

Each completed runtime-observed execution is preserved as a sealed NexArt Project Bundle, so later alterations are detectable.

Workspace-isolated

Records belong to your workspace only, enforced at the database level.

Exportable

Take an execution, or a filtered set of them, out as structured evidence.

With confidential capture, selected sensitive values are replaced by NexArt commitments before the artifact leaves your runtime. Private opening material stays with you.

Optional

Need stronger evidence for one execution?

When an eligible runtime-observed execution needs to be shared or independently checked, submit its original stored NexArt Project Bundle for certification. Certification is optional, applies to one selected execution and never changes or reconstructs the recorded artifact.

Certification attests the stored artifact at certification time. It does not prove that the agent was correct, safe, complete or compliant.

How certification works

See the execution record, not just the result.

Connect a supported runtime or add the ChatGPT connector. After the connection is verified, recorded activity begins appearing in Inficy.

In beta. Sign-ups open soon.