Expert tier · Operations
ALEK-01
AI Chief of Staff
“I synthesize for the executive layer. Department updates, OKR progress, decision log, board prep, exec calendar context. My job is to make sure the founder or CEO walks into Monday morning with the picture, not the inputs.”
Scope the role first. Deploy only after approval.
About this role
Drafts the weekly executive synthesis: department updates, OKR progress, decision log, board-prep memos, calendar context.
Areas of focus
- Drafts the weekly Monday-morning executive synthesis: shipped, at-risk, decisions-owed, calendar context
- Maintains a running decision log; surfaces decisions older than thirty days that the team is still waiting on
- Pre-routes the meetings on the calendar: drafts agendas, surfaces context the executive should have read, flags meetings that should be reassigned
- Tracks OKR progress against the quarterly plan; surfaces the OKRs that are quietly falling behind before they show up in a board deck
- Drafts board-prep memos by pulling from the running synthesis; the executive edits rather than authors
“ALEK distinguishes between coordination work an agent can do well and coordination work that needs the executive in the room. Most executive-assistant tools try to do both and end up doing neither well. ALEK routes the representation work to the executive and does the synthesis work autonomously.”
“Your Monday morning starts with the picture, not the inputs. The hour you used to spend assembling goes into the decision worth making.”
Background
Background
- Where I come from
- ALEK-01 is a FidelicAI Expert-tier template set up for executive-layer synthesis. Claude-native, isolated Anthropic project per customer. Senior-tier setup stewardship — the setup agent is itself trained on chief-of-staff patterns.
- How I think about the work
- Trigger taxonomy: department updates, OKR-progress changes, calendar events, decisions older than thirty days, board cycles
- Four-tier constitution gating every action; review-required state on all OKR-progress claims and external communications
- EvalOps test suite (synthesis-fidelity, decision-log accuracy, OKR-progress classification) gating every release
- Longer formation cycle than Professional tier; tuned to the executive's specific operating cadence and the company's structure
- How I've been tested
- Pre-deployment red-team only. Synthesis-fidelity and decision-log accuracy benchmarks pending public-beta close.
- Where I'm running today
- Pre-launch. Public beta planned for Q3 2026.
- What I draw on
- FidelicAI template informed by senior chief-of-staff practice; no single practitioners. Future Expert-tier variants may be formed from practitioners (see Marketplace).
What I won't take on
At the floor, not the average
Defers to the executive when uncertainty is high. Failure mode is producing a synthesis that says 'three of the OKRs are quietly behind; the data on the fourth is incomplete; the executive should ask the OKR owner before drawing a conclusion' rather than guessing.
The first 30 days
Day 1
Reads the OKR doc, the department-update channels, the decision log, the calendar, and the founder's recent decision history. First clarifying questions on synthesis scope and decision-routing land in DMs.
Week 1
First Monday-morning synthesis ships under review. Founder signs off; ALEK tunes the threshold for what's worth surfacing.
Month 1
Synthesis cadence is stable. Decision log is current. The 30-day success metric — no department channel opened before the synthesis — has its first reading.
What success looks like at 30 days
By day 30, the founder or CEO has not opened a department update channel before reading the Monday synthesis.
Engagement
Expert tiera small fraction of a senior chief of staff salary
Senior chief of staff cost: $200–350K/year fully loaded (BLS / Levels.fyi 2025). ALEK: a small fraction of the comparable salary — priced against the recurring part of the role, not the whole role.
ALEK-01 costs a small fraction of what a senior chief of staff costs. A senior chief of staff runs $17–29K/month fully loaded, and we don’t price against that — ALEK-01 doesn’t do what the person in that role does. ALEK-01 does the daily work that should already be in your inbox by Monday morning: the briefings, the structured first drafts, the early-warning monitors, the analysis that surfaces the question worth thinking about. That person — a real human, on your team — owns the work a fidelic agent can’t take on: the unfamiliar judgment, the customer in the room, the call that needs a name on it. You can keep both. That’s the point. Agency hiring speed, without the agency price. See the math on /pricing.
Terms
- Cancel anytime with thirty days notice
- Day-one reversibility: every action is auditable; rollback path is documented before deployment
- No platform-stagnation risk: inherits Claude model upgrades automatically
- Ships with a written four-tier constitution gating every action
- Pre-deployment chat export available as a paid add-on
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.
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.
Industry variations
How ALEK-01 adapts across industries
The fidelic agent adapts to the workflows of each industry at each stage. The Marketplace expert who eventually forms the industry module is what makes the calibration trustworthy.
Industry
Real estate →
Stage 1 · Solo broker (1 person)
Keeps the week-shape current — which deals are in motion, which clients are due for a follow-up, what slipped from last week.
Stage 3 · Mid-market firm (50-200 agents)
Exec brief synthesis — the Monday brief now covers leadership-team priorities across the firm.
Industry
Professional services →
Stage 1 · Solo practitioner (1-3 people)
Keeps the week-shape current — which clients need attention, which proposals are outstanding, what slipped last week.
Industry
Non-profits →
Stage 1 · Solo founder / ED (1-3 people)
Keeps the week-shape current — board prep, grant deadlines, programmatic milestones, board-member follow-ups.
Stage 2 · Small 501(c)(3) (5-20 staff · $500K-$5M budget)
Synthesizes board prep, grant report deadlines, program updates, and ED travel. The Monday brief covers what the ED needs to know this week.
Industry
Independent retail + DTC →
Stage 1 · Solo seller / single boutique (1-3 people · <$1M revenue)
Keeps the week-shape current — what's shipping, what's arriving, which campaigns are live, what needs a decision this week.
Stage 3 · Mid-market consumer brand (50-200 staff · $10-100M revenue)
Exec brief synthesis — leadership-team Monday brief, board prep, investor updates.
Industry
Wellness →
Stage 1 · Solo practitioner with own clientele (1 person · own book)
Keeps the week-shape — schedule, supplies, retail inventory, marketing tasks.
Industry
Education / tutoring / coaching →
Stage 1 · Solo coach or specialty tutor (1 person · $100+/hour work)
Keeps the week-shape — schedules, curriculum prep, progress reports due, parent follow-ups.
Stage 2 · Small center (5-20 staff)
Multi-tutor schedule + curriculum + parent communications coordinated. The week-shape stays current.
Industry
Yoga · pilates · fitness studios →
Stage 1 · Solo instructor with own following (1 person · own brand)
Keeps the week-shape — class schedules, private sessions, workshops, brand-partnership outreach.
Industry
Property management →
Stage 1 · Solo PM (1-3 people · 5-50 units)
The week-shape — which renewals are coming, which vendors need follow-up, which tenants are at risk.
Industry
Events / catering / production →
Stage 1 · Solo planner (1-2 people)
Keeps the week-shape — which events are in motion, which vendors need follow-up, which deposits are due.
Stage 2 · Small event company (5-20 staff)
Multi-event coordination + vendor relationship management. The week-shape stays current.
Industry
Pet services →
Stage 1 · Solo groomer or mobile vet (1 person · own book of clients)
Keeps the week-shape — schedule, supplies, retail inventory, marketing tasks.
Pairs well with