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 that scales and coordination work that requires representation. 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 Fidelic AI Expert-tier template configured for executive-layer synthesis. Claude-native, isolated Anthropic project per customer. Senior-tier configuration stewardship — the configuration 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; calibrated 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
- Fidelic AI 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 calibrates 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 part of the role that scales, not the whole role.
ALEK-01 costs a small fraction of what a senior senior chief of staff costs. A senior senior chief of staff runs $20–30K/month fully loaded, and we don’t price against that — ALEK-01 doesn’t do what a senior person 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. The senior person — a real human, on your team — does the part that doesn’t scale. You can keep both. That’s the point. 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 lands
Every Fidelic agent ships with a published operating plan. You know what it will do before you pay.
- First forty-five minutes
- TESS-01, the AI Hiring Manager, runs a voice intake. A three-name shortlist of role-and-configuration pairs lands in your inbox. You pick one. Slack OAuth. The agent appears in your Slack.
- Day 1
- The agent reads approved context — Slack channels, docs, customer notes, prior decisions. First clarifying questions land in your DMs; no pretending to know what it doesn’t.
- Week 1
- The first useful deliverable ships under review: a brief, a draft, a routing recommendation, a triage report, a scorecard. You sign off; the configuration agent calibrates.
- Month 1
- The role is operational. Escalation patterns are calibrated. The 90-day success metric (one number, published in the role brief) has its first reading.
Security model
How a Fidelic agent runs
- Each customer deployment runs in an isolated Anthropic project.
- Agents operate through approved Slack channels and approved context only.
- Fidelic logs operational metadata, not message or file contents.
- Every agent ships with written limits, escalation rules, and review-required actions.
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