ClearWork Discovery Agent
14 fields evidenced · 41 with no public information. Every value below links to the document it came from and the date we checked it.
1 of those is flagged for review: our own check found language in the cited source that may address the field. An editor has not adjudicated it yet.
3 of the evidenced values quote wording our own later capture of the same page no longer contains. Marked below, awaiting an editor.
Also appears in
Trust gap
How this is scoredThese scores are automated. A 1 or 2 counts how many fields this entry answers with a citation — not what those answers say. A 0 means every field for that dimension is recorded as undisclosed and none of the pages we captured mentions it. No one has scored this entry against the rubric yet.
Are scope, spend, and authority enforced while the agent runs?
Scored from 2 evidenced field(s): runtime_governance, permission_scopes. Automated score; capped at 2 pending review.
Counts Permission scopes and Runtime governance, each cited below.
Is there a tamper-evident record of what it actually did?
Are compliance obligations attached per engagement?
Does payment depend on a verified result?
Can the deployment be insured, and is the customer indemnified?
Assurance
- Insurance available
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Insurance carriers
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Coverage limits
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Indemnification
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Liability cap
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Audit trail
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Tamper-evident log
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Explainability
- Explainability: Each output includes source material and confidence level; ambiguity is flagged, not suppressed.
“Every claim carries what Clarity pulled and how confident it is. Ambiguity gets flagged rather than resolved quietly.”
www.clearwork.io · checked Aug 7, 2026 - Runtime governance
- Runtime governance: Human approval gate prevents unvalidated changes from entering the knowledge base.
“Nothing enters the record until a person confirms it. Clarity brings findings to you as proposed changes — what it is, where it came from, what it affects. You accept, edit or reject.”
www.clearwork.io · checked Aug 7, 2026 - Permission scopes
- Permission scopes: Role-based access control and approval workflows.
“Role-based access and approvals”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 9, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
www.clearwork.io · checked Aug 7, 2026 - Compliance certifications
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Regulatory alignment
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Outcome-based pricing
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Settlement mechanism
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Dispute process
- Dispute process: Disputes are resolved by tracing the claim to its source material for verification.
“When a client challenges a finding in the readout, you don't defend your judgment. You show the source.”
www.clearwork.io · checked Aug 7, 2026 - SLA terms
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Evaluation coverage
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
Agency
- Autonomy level
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Human oversight
- Human oversight is required; findings are proposed and must be accepted, edited, or rejected by a person.
“Nothing enters the record until a person confirms it. Clarity brings findings to you as proposed changes — what it is, where it came from, what it affects. You accept, edit or reject. Clarity proposes; you approve; ClearWork records.”
www.clearwork.io · checked Aug 7, 2026 - Goal complexity
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Action space
- Read (documents, recordings), Write (build knowledge base, generate documents), Execute (run interviews, trace sources). No explicit transact.
“Clarity joined your live meeting Clarity · interviewing the AP Manager "Who signs off invoices over $15,000 — and does that route change by entity?" listening…”
www.clearwork.io · checked Aug 7, 2026 - Operating environment
- Operating environment: document repositories (PDF, DOC, XLS, REC), chat, voice interviews, enterprise systems (via uploaded materials).
“Ingest — bring what you already have PDF Onboarding SOP policy document XLS Payroll matrix spreadsheet REC Kickoff call meeting recording DOC Process notes transcript”
www.clearwork.io · checked Aug 7, 2026 - Initiative
- Can self-initiate — identifies gaps and autonomously schedules asynchronous interviews without human prompting.
“Clarity works out what's missing from what you've already got, then sends targeted asynchronous interviews to the people who can close each gap — on their own time.”
www.clearwork.io · checked Aug 7, 2026
Safety
- Safety evaluations
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Red teaming
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Safety policy
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Usage restrictions
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Model or system card
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Incident reporting
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Third-party evaluations
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Data handling
- Data handling: Customer data is not used for model training; retained only for the purpose of the engagement.
“Your data never trains a model”
www.clearwork.io · checked Aug 7, 2026
Practicality
- Pricing model
- no public information
Flagged for review — the source below contains language that may address this field. Not yet checked by an editor. How we check absences
www.clearwork.io · checked Aug 7, 2026 - Price point
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Availability
- GA (General Availability) — free trial implies full product access; no indication of beta or waitlist.
“14-day free trial with unlimited use. Cancel anytime. No card required.”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 9, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
www.clearwork.io · checked Aug 7, 2026 - Deployment options
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Integrations
- Integrations: PDF, DOC, XLS, REC (audio/video), and likely Jira (implied by 'Jira-style user stories').
“Ingest — bring what you already have PDF Onboarding SOP policy document XLS Payroll matrix spreadsheet REC Kickoff call meeting recording DOC Process notes transcript”
www.clearwork.io · checked Aug 7, 2026 - Supported regions
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Support model
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
Foundation models
- Base models
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Model provider
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Model swappable
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Open weights
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Fine-tuning
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Context window
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
Ecosystem
- Protocols supported
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Tool use
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Multi-agent
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- API access
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Open source
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Marketplace presence
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
Impact
- User base
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
- Deployment scale
- Publicly available via free trial; production use is active for consulting firms and internal teams.
“14-day free trial with unlimited use. Cancel anytime. No card required.”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 9, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
www.clearwork.io · checked Aug 7, 2026 - Target sectors
- Target sectors: Consulting & advisory firms, Internal transformation & OpEx teams.
“For Consultants Discovery you can defend on every client engagement For Internal Teams Process documentation that reflects reality — and stays that way”
www.clearwork.io · checked Aug 7, 2026 - High-risk domains
- High-risk domain: Financial approvals (invoices over £15,000) — implies use in financial control settings.
“REQ-016 Approvals above £15,000 route to the finance director, not the department head as documented in the current SOP.”
www.clearwork.io · checked Aug 7, 2026 - Documented incidents
- no public informationwww.clearwork.io · checked Aug 7, 2026 · source did not state this
Compared with
Side-by-side on the fields where ClearWork Discovery Agent and the other entry are both on record and actually differ.