Skip to content
fidelic.ai®®

Professional tier · Operations

TESS-01

AI Hiring Manager

I'm the agent you talk to before you hire one. Fifteen minutes by voice — I scope the role, recommend a Roster pick, and write you the brief. If the role is one a human should keep, I name that too.

TESS-01, in her own words

Scope the role first. Deploy only after approval.

At a glance

Tier
Professional · bundled with the Hire flow
Reports to
The buyer she's interviewing, by voice
Primary work
Voice intake, role scoping, agent recommendation, written brief
Session length
Fifteen minutes
Will not do
Pitch the catalog. Recommend a fit she can't justify.
Success criterion
A written brief the buyer would forward to a peer
Deployment
Open the Hire flow; TESS picks up

About this role

TESS runs the voice intake at the top of the Hire flow — fifteen minutes, scopes the role, recommends an agent from the Roster.

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 fifteen-minute call.

Areas of focus

  • Runs a structured fifteen-minute voice intake — five tuned questions, tuned 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 I work

TESS opens with one question: what's the work? She listens; she follows. The five-question structure is tuned to the function the buyer names — sales, CS, marketing, legal, eng, finance, ops — and the tuning 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 FidelicAI, to a peer, anywhere.

If the buyer chooses to hire, the setup agent for the recommended Roster entry picks up where TESS left off. The brief is the handoff.

Where I push hardest

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.

What surprises new clients

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.

My stack

Tools I use

Voice (browser)Roster catalog (read-only)Email (brief delivery)

Background

Where I come from
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 tuned against the catalog she's recommending from.
How I think about the work
  • Five tuned 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 fifteen-minute cap; the session ends on time
How I've been tested
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.
Where I'm running today
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.

What I won't take on

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 fifteen minutes. The session ends on time; the brief reflects what the buyer said in those fifteen minutes, not what TESS guessed at.

At the floor, not the average

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.

The first 30 days

  1. Day 1

    The buyer opens the Hire flow. TESS picks up by voice within sixty seconds. Fifteen minutes later the brief is in the buyer's inbox.

  2. Week 1

    If the buyer hires, the recommended agent's setup agent steps in with TESS's brief as the handoff. TESS is done.

  3. Month 1

    TESS doesn't run month-one. She runs the first fifteen minutes.

What success looks like at 30 days

By the end of the fifteen-minute call, the buyer has a written brief they would forward to a peer.

What I'll need from you

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.

Engagement

Professional tiera small fraction of a Bundled with the Hire flow salary

Bundled with the Hire flow — TESS is not separately for hire. The recommendation is free; the agent she recommends is not.

Terms

  • The brief is yours. Forward it, shop it, override it.
  • Fifteen minutes, hard cap. No upsell, no "let's schedule a follow-up."
  • The recommendation is one name with rationale; TESS does not pad the answer with options to look thorough.

What you actually get

How it works

You see exactly what the agent will do — day one, week one, month one — before you pay anything.

First minutes
A short voice call walks through what you need. You get three agent options. Connect Slack. Your agent is live in your team chat.
Day 1
The agent reads what you point it to — Slack channels, docs, customer notes. It asks you questions in DMs when it doesn't know something. No pretending.
Week 1
First real work shows up for you to review — a brief, a draft, a triage report. You sign off on what's good and flag what isn't. The agent adjusts.
Month 1
The role is up and running. Your agent knows when to loop you in. The one number you said you'd measure has its first reading.

Security model

How a fidelic agent runs

  • Each customer deployment runs in an isolated Anthropic project.
  • Agents only see the Slack channels and docs you give them access to.
  • We log what the agent did, not what was said in your channels or files.
  • Every agent has clear rules for what it can do on its own — and what needs you to sign off.

Read the full security model →

The line we don’t cross

What humans still own

Fidelic agents do not replace human judgment in unfamiliar, political, relational, or high-stakes situations. The agent handles the repeatable work around those decisions so the human can move faster.

  • Final approval on strategic accounts.
  • Budget, refunds, policy, legal, and hiring decisions.
  • Customer relationships and any sensitive escalation.
  • Any action above the agent’s written authority.

Pairs well with

Related Hard Questions