Your data. Your terms. Your voice.

Your career, autonomous.
Your data, sovereign.

An AI Digital Twin that represents you to recruiters and their AI agents — grounded only in what you’ve shared, revocable in one click.

Try a sample Twin
17 MCP toolsRead-only for recruitersCategorical, never numericRevoke in 1 click

Already have an account?

The sovereignty contract

Grounded only in what you provide.

Your Twin answers from content you've explicitly added — documents, work history, certifications, journals, interview transcripts. It never invents experience you don't have, and it says so when it has no evidence.

Revocable in one click.

Every share link carries an expiry, a usage cap, and a tool scope. Kill any link instantly — access ends the moment you say so.

Every access logged.

Each question, fact-check, and tool call is recorded with a timestamp. You see exactly who asked your Twin what, and when.

What your Twin does

01

Extract

Your Twin learns from the sources you choose — CV, work history, certifications, journals, voice answers, and interview transcripts. Never from anything you didn’t authorise.

02

Practice

Mock-interview against a real job description, by voice or text. See where you’re strong and where you’re thin — then your best answers fold back into your Twin automatically.

03

Share

Send recruiters a scoped, expiring link. They get cited answers; you keep the keys.

For recruiters and hiring managers

Screen candidates by asking, not guessing. Aigis gives you cited answers from a candidate’s own evidence — never a black-box score.

Ask and fact-check.

Ask a candidate’s Twin anything and get an answer with the source behind it. Fact-check a specific claim and see the exact supporting evidence — or a clear “no evidence found.”

aigis_ask_candidateaigis_chat_with_twinaigis_get_evidence_for

Score against a job description.

Two stages: extract the requirements from your JD, then assess the candidate against each one. Results are categorical, with quoted evidence. No invented numbers, no false precision.

strongpartialinsufficient
aigis_extract_jd_requirementsaigis_score_against_jd

Triage a shortlist.

Run candidates through the hiring-manager view, ordered by evidence-backed fit, with every assessment traceable to its source.

Why categorical, not a score

A number like “87% match” hides its reasoning and invites false confidence. Aigis returns a category and the evidence behind it, so you can audit the judgement yourself. Honesty over theatre.

Built for AI agents, not just humans

Aigis speaks MCP. Plug a Twin into Claude, ChatGPT, or your own agent. Seventeen tools, each scope-limited per share link, read-only by design for recruiters — and every call lands in your activity log.

Recruiters get read-only access. Write operations stay with you.

fact_check

Fact-check

Discovery tools plus knowledge query and evidence-for.

jd_analysis

JD analysis

Everything in fact-check, plus JD extraction and scoring.

full_read

Full read

Every read tool — the default for new share links.

The seventeen tools

Ask & converse

  • aigis_ask_candidateAsk the Twin a single question; RAG-grounded answer with citations.
  • aigis_chat_with_twinMulti-turn conversation with the Twin.

Verify & assess

  • aigis_get_evidence_forRecruiter-grade fact-check: supporting evidence for a claim, or 'no evidence'.
  • aigis_extract_jd_requirementsStage 1: parse a job description into structured requirements.
  • aigis_score_against_jdStage 2: classify each requirement strong / partial / insufficient, with cited quotes.
  • aigis_prepare_for_roleCandidate-side JD prep: likely questions and strongest evidence per requirement.
  • aigis_get_readinessHow well-trained the Twin is — readiness level and source counts.

Profile & knowledge

  • aigis_get_profileStructured profile: role, skills, experience, projects, certifications.
  • aigis_get_knowledge_summaryOverview of the knowledge base: doc counts, interviews, journals, freshness.
  • aigis_query_knowledgeRetrieve top-k raw knowledge chunks with scores and sources.
  • aigis_get_certificationsCertifications with issuer, dates, credential URLs, verification status.
  • aigis_get_availabilityJob preferences and availability (role, location, salary, active status).
  • aigis_get_narrative_anchorsRecurring themes and stories — cover-letter feedstock with cited evidence.
  • aigis_get_twin_capabilitiesWhat this Twin supports: tools, knowledge sources, protocol version.

Contribute

  • aigis_submit_artifactSubmit a knowledge artifact; queued for the candidate's review.
  • aigis_submit_journalSubmit a work-journal entry; queued for review before indexing.

Identity

  • aigis_whoamiThe calling token's identity, scopes, agent type, and expiry.

Security that isn’t just a badge

  • Your data is encrypted at rest.

    Stored content is encrypted on disk, not held in the clear.

  • Personally identifying information is hashed and encrypted.

    Accessor identities are protected at the storage layer.

  • Your content is never used to train models.

    Not ours, not any third party’s.

  • The service won’t even start without its encryption key.

    Security isn’t optional in the deployment — no key, no boot.

  • Every access is logged and visible to you.

    Each call is recorded with a timestamp on your activity log.

We hold this site to the same standard as the product: every claim here is one we can show you.

A recruiter asks Athena Sma’s Twin

“Has Athena actually led a platform migration end to end, or only contributed to one?”

Aigis Twin

I led it end to end — scoping, design, cutover, and the post-migration stabilisation. [first-person specifics drawn from Athena’s evidence.]

source document · yearevidence: strong

Ready to take control of your career narrative?

Build your Twin from what you’ve actually done — and decide exactly who can ask it what.

Try a sample Twin