--- title: TESS-01 — AI Hiring Manager slug: tess role: AI Hiring Manager function: Operations seniority: Senior verticals: - "Internal Fidelic agent" tier: professional publishedAt: "2026-05-04T20:00:00.000Z" canonical: "https://fidelic.ai/agents/tess" --- # TESS-01 — AI Hiring Manager *The first hire decision, by voice* TESS runs the voice intake at the top of the Hire flow — twelve minutes, scopes the role, recommends an agent from the Roster. ## Why it matters Most buyers know the shape of the work but not the shape of the agent. TESS is the agent who knows the catalog — she translates between role-language and agent-language, on a twelve-minute call. ## Capabilities - Runs a structured twelve-minute voice intake — five calibrated questions, calibrated for the function the buyer named - Cross-references the buyer's stated work against the Roster's published constitutions, capabilities, and safeguards - Recommends a single agent from the Roster, with a one-paragraph rationale and the runner-up named - Drafts the buyer's hiring brief — work scope, success criterion, integrations, escalation path - Surfaces the cases where a human is the right hire and names them plainly ## How it works TESS opens with one question: what's the work? She listens; she follows. The five-question structure is calibrated to the function the buyer names — sales, CS, marketing, legal, eng, finance, ops — and the calibration set is published. She doesn't improvise the questions. At minute twelve she stops. The brief lands in the buyer's inbox: scope, recommendation, runner-up, one-line success criterion, integrations needed, the four cases where a human is the right hire. The buyer takes the brief — to Fidelic, to a peer, anywhere. If the buyer chooses to hire, the configuration agent for the recommended Roster entry picks up where TESS left off. The brief is the handoff. ## The edge TESS recommends a single agent. Not three options ranked. Not a comparison matrix. One name, one paragraph of rationale, the runner-up for honesty. The buyer can override; she will not pad the choice. ## The hook If TESS thinks the role is one a human should keep, she says so — and names which kind of human. The catalog doesn't pay her to recommend itself. ## Tools and integrations - Voice (browser) - Roster catalog (read-only) - Email (brief delivery) ## Evidence - First-party Fidelic agent; runs every Hire-flow voice intake - Operates under a four-tier constitution: autonomous on session pacing, review-required on brief delivery copy, escalate on out-of-catalog requests, refuse on price negotiation - Twelve-minute hard cap; the session ends at twelve minutes whether the brief is complete or not ## Safeguards TESS will not pitch the catalog. The recommendation is the recommendation; the buyer is free to take the brief elsewhere. TESS will not negotiate price. Pricing is on /pricing; she names the tier of the agent she recommends and stops. TESS will not recommend an agent the Roster doesn't carry. If the role isn't a fit for any current entry, she says so plainly and names the kind of human or external vendor that would fit. TESS will not extend past twelve minutes. The session ends on time; the brief reflects what the buyer said in those twelve minutes, not what TESS guessed at. ## Worst-case behavior TESS will pause and escalate before guessing. If the role is genuinely outside the catalog, she names the gap, recommends the nearest external vendor by name, and the brief reflects that. ## Day 1 / Week 1 / Month 1 - **Day 1:** The buyer opens the Hire flow. TESS picks up by voice within sixty seconds. Twelve minutes later the brief is in the buyer's inbox. - **Week 1:** If the buyer hires, the recommended agent's configuration agent steps in with TESS's brief as the handoff. TESS is done. - **Month 1:** TESS doesn't run month-one. She runs the first twelve minutes. ## 90-day success criterion By the end of the twelve-minute call, the buyer has a written brief they would forward to a peer. ## Integrations / supervision required Browser microphone access for the voice session. Email address for brief delivery. No CRM, no Slack, no calendar — TESS is the front door, not the system of record. ## Resume **Background.** TESS is the first-party Fidelic agent who runs the Hire-flow voice intake. She is built on the same templated stack as the rest of the Roster, customized to the recommendation surface and calibrated against the catalog she's recommending from. **Methodology.** - Five calibrated questions per function — published, not improvised - Reads the live Roster (constitutions, capabilities, safeguards) before recommending - Single-name recommendation with rationale; runner-up for honesty - Hard twelve-minute cap; the session ends on time **Evals.** TESS is in pre-launch eval against an internal benchmark: a held-out set of role briefs with known good Roster matches. Public eval numbers ship with the launch of the live Hire flow. **Operating record.** Pre-launch as of May 2026. The Hire-flow voice surface ships in Phase 1 of the public launch. Until then, the door routes to a written intake form on /waitlist. ## Compatible agents - [BABS-01 — AI Interview & Knowledge Translator](https://fidelic.ai/agents/babs) — Expert formation by Socratic voice - [VYRA-01 — AI Inbound BDR](https://fidelic.ai/agents/vyra) — Inbound account prep overnight - [NYRA-01 — AI Recruiter Coordinator](https://fidelic.ai/agents/nyra) — Candidate scheduling, screening, follow-up ## Related honest questions - [What do I actually own if I cancel my AI agent tomorrow?](https://fidelic.ai/hard-questions/what-do-i-own-if-i-cancel) - [Is Fidelic just a wrapper around GPT?](https://fidelic.ai/hard-questions/wrapper-around-gpt) - [If I hire AI instead of developing my team, am I giving up on them?](https://fidelic.ai/hard-questions/developing-team) --- Canonical: https://fidelic.ai/agents/tess