Sidekick Orchestration
SoloFractionalHow It WorksGuidesFAQ
// How it works

We run on this too.

This is the actual system we run Sidekick on, the same one we build for you. The repetitive work between your tools gets done, checked, and handed back for your okay.

Your tools stay.
The busywork between them goes.

It is one place that does your repeat work, checks itself, and never sends anything without your say-so.

Your tools
GmailHubSpotCalendarSlackDriveAutomations
LiveOne AI workspaceClaude keeps the context and sends each job to the right skill.
01Daily Operations
  • Inbox Triagesorts and drafts your email
  • Meeting Notessummarizes your calls
  • Action Itemstracks every to-do
02Sales Pipeline
  • Pipeline Pulseflags deals going cold
  • Prospect Prepbriefs you before calls
  • Outreach Draftswrites your follow-ups
03Content + Reach
  • Email Voicereplies that sound like you
  • Posts + Blogdrafts your content
  • AI Searchget found by AI assistants
04Clients + Back-office
  • Client Healthspots quiet clients
  • Weekly Reportassembles your week
  • Knowledge Basekeeps it all findable
You approve everythingEvery email, post, and message is drafted and staged. Nothing sends until you say go.
Work, ready to ship
It checks its own work against a quality bar before you ever see it.

You give it the idea. It hands back finished work, not a rough draft.

One-shot is a real skill we built into this workspace. Most AI gives you a first draft and a to-do list. One-shot does the whole job in one run, researches it, plans it, builds it, then grades its own work and fixes the gaps before you ever see it.

What a skill isA saved, repeatable workflow, a process the system runs the same way every time. One-shot is one of ours, shown here in action.

Your ideaone-shotPolished output
01
Research
Gathers the context, sources, and references the work actually needs, instead of guessing.
02
Plan
Locks the goal and writes the bar the output will be graded against, before building anything.
03
Build
Produces the work step by step, checking each step before it moves to the next.
04
Self-eval loop
Scores its own output against that bar, fixes the exact gaps, and re-scores until it clears, or stops and tells you.
It catches its own mistakes
Most AI tools fail by snowballing: one early slip quietly bends everything after it. This checks itself between every step, so small errors get caught before they compound.
You control what matters
Routine work runs start to finish. Anything that sends, publishes, or touches money or a client stops for your approval. You stay in charge of the high-stakes moments.
Nothing is a black box
Every choice it makes is written down, so you can see the reasoning and reverse any decision after the fact.

Not a demo. This is how we run.

40+
tasks it handles
6
tools connected
0
sent without your approval

The whole thing, in detail.

Everything above is the shape of the system. This is the full specification: what is inside it, how each layer works, what it solves, and where its real limits are. It is written for someone already using AI seriously who wants the mechanism, not the brochure. Everything here is the system as it runs today, measured failure rates and platform limits included. We would rather you decide on the true shape of the thing than on a polished version of it.

Every component below sits in one of five layers. The improvement engine is the loop that feeds what each layer learns back into the template every layer is built from.
01 · INSTRUCTION LAYERCLAUDE.md: identity, routing, memory and safety rules. Loads every session.02 · MEMORYSemantic, episodic, procedural files. Rewritten to present truth, never appended.03 · SKILLS40+ skills plus custom ones built for you, wrapped in trigger phrases.04 · OPERATING SURFACELive dashboard, daily and weekly cadences, guides, the first-win on-ramp.05 · QUALITY GATE8 floor gates, 10 dimensions, a first-week simulation. Nothing ships below green.IMPROVEMENT ENGINE
Five layers, one loop. The architecture every build is assembled from.
01 · What it solves

AI workspaces decay by default

Adopt Claude or ChatGPT seriously and the first few weeks feel like progress. Then the slide starts. The same failures show up across very different people, in the same order, and they compound quietly enough to look like the model getting worse. It does not get dumber. It gets buried.

01
Memory is shallow and uncurated Without the system
The big tools carry facts across sessions now, which is exactly why the first weeks feel great: it starts to know you. But the memory keeps whatever passes through, with no sense of what is current, what matters, or what should have been dropped. It pulls some things forward and quietly misses others, and the gaps surface right when you had started to trust it.
02
Instructions pile up and contradict Without the system
Most setups grow by appending. New priorities sit next to old ones, current facts beside stale ones, and nothing is ever removed. The file meant to make the assistant smarter becomes the thing making it unreliable. The longer you use it, the worse this gets.
03
Output sounds like the model, not you Without the system
A paragraph describing how you write produces something generic with shorter sentences. A description of your voice is not your voice, the same way a new hire handed your LinkedIn page could not sign your emails. You edit everything heavily or stop delegating writing at all.
04
Usage plateaus at chat Without the system
With no named workflows, trigger phrases, or first win, usage stays at ad-hoc questions. The recurring work that would justify the tool never moves onto it.
The compounding cost

None of these is dramatic on day one. By week six the workspace is a junk drawer, you trust it less than at the start, and the honest read is that the tool never paid back its own learning curve. That is what turns “it knows me” into “it has gotten worse.”

Want the plain-English version of this? Read Why Your AI Gets Worse the More You Use It.

02 · What you receive

You get a workspace that gets better the more you use it

The deliverable is not a clever prompt pack. It is an operating environment that gets more useful with use: context compounds, corrections become rules, and improvements made anywhere in the system propagate forward into every new build. Every build starts as a copy of the Master Template (currently v1.9) and is populated with your context. It is plain files in a folder you own. No database, no proprietary runtime, fully inspectable and portable.

Your workspace/
|-- CLAUDE.md the instruction layer; loads at every session start
|-- Start_Here.md one-page entry point, names your first-win task
|-- Your_Workflows.md your 2-3 highest-priority workflows, copy-paste prompts
|-- INDEX.md master map of every file in the workspace
|-- Starter_Prompts.txt the full skill routing table: trigger phrases
|-- Skills/ 8 day-one skills + Skills/Operator/ (30-skill library)
|-- Guides/ branded PDF guide set, dashboard template, Your First Month
|-- Reference/ Business + Comms profiles, Current_State, Action_Items, Decisions
|-- People/ one context file per key relationship
|-- Meetings/ structured call notes, one file per meeting
`-- SOPs/ · Active/ · Deliverables/ your processes, work in progress, finished output

A few root files carry the day-one load: Start_Here.md (how to start a session and your named first win, no placeholders), Your_Workflows.md (your priority workflows with copy-paste prompts), and Starter_Prompts.txt (the routing table that makes triggering reliable). A reader who opens the folder cold finds an entry point, a map, and no internal build artifacts.

03 · Memory that compounds

The index is what makes memory reliable

Most people run their AI memory like a junk drawer: everything goes in, nothing comes out, and eventually you are afraid to open it. The fix is a handful of boring disciplines, none of which need a better model. CLAUDE.md is the one file the platform reliably loads at session start, so it carries everything that must always hold: identity, the routing table, the memory rules, and the safety rules.

Give the workspace an index. A simple map of every file and what it holds lets the model look up the one relevant, current thing and read just that. With no index, it rereads the entire filing cabinet to answer one question, fills its working memory (the context window) with noise, and forgets the answer. People read that as the model getting forgetful. What is really happening is it has more memory than it can sort, so it holds all of it at once and weights none of it. The index is also where relevance and recency get decided. For most people hitting the “it cannot remember anything” wall, this is the highest-impact fix almost nobody has in place.

Rewrite the state, do not append to it. The current-state file is rewritten at the end of each session so it always reflects what is true now, instead of stacking session recaps until it contradicts itself. This single discipline kills most of the instruction-pileup decay on its own.

Route memory by type. What is true now (priorities, business, people) lives in one place. What happened when (decisions, meeting notes) lives in another. How things get done (standing rules, workflows) lives in a third. Every “remember this” is sorted to the right type before it is written, so the assistant can actually find it later.

Why this matters

Every drafting and analysis skill reads this layer before producing anything, which is why output quality scales with workspace age here and degrades with it elsewhere. The architecture is the moat; the prompts are replaceable. A weekly scheduled lint pass catches stale content, contradictions, and dead references before they mislead a session.

04 · The skills library

Most builds run 40+ skills, built around your work

A skill is a saved specification that wraps a recurring piece of judgment: what to read, what to produce, what never to do. A core set is active from day one, and a deeper library opens up as your usage matures, so most builds end up running more than 40 skills in total. Every skill carries explicit trigger phrases, because manual triggering is the reliable path on this platform (more on that under limits).

Day-one skillWhat it does
sessionOpens and closes the session: reads context, then updates current state, logs decisions, and integrates corrections. The ritual that makes everything else persistent.
daily-briefA sub-3-minute morning orientation from priorities, action items, decisions, meetings, and live calendar, email, and CRM where connected.
post-callRaw notes or a transcript in; structured meeting notes, signals, a follow-up draft, and a next action out, in one pass.
quick-capture“Remember this” routed to the right file and confirmed in one line. No questions, no analysis.
action-itemsThe live task ledger: add, review, filter by person, prioritize, hygiene sweep. The owner column drives the dashboard split.
meeting-prepA one-page brief for an upcoming meeting: agenda, objectives, relationship context, recent signals.
executive-commsDrafts a message to a named recipient in your calibrated voice and their register. Never sends without approval.
dashboard-renderRenders the live daily dashboard from your action items, decisions, and current state.
Operator library · introduced as usage matures
Documentscontent, docx / pptx / xlsx, outreach, prompt-sharpener: long-form writing, branded documents, and drafts in your voice.
Planningplan / build, decision-brief, strategic-analysis, board-prep: multi-step work spec-locked, scored, and steelman-first.
Voicemy-voice / voice-extractor, stakeholder-comms, people-intelligence: voice pulled from real samples, multi-audience handling.
Emailinbox-organizer, email-drafter: triage plus reply drafting staged in Gmail. Never sends.
Meetingsmeeting-intelligence, week-ahead / weekly-review: transcript processing and the weekly cadence.
System healthfeedback-loop, sop-capture, tune-this, quality-loop, workspace-eval, context-lint, update-diff, monthly-review, schedule.
Custom skills, scoped to you

The baseline: we turn your two or three highest-impact workflows into custom skills, with trigger phrases rich enough to catch the natural ways you would ask. From there it grows with you. Once those first workflows are running, the coaching tends to surface the next ones, and clients who take the coaching often finish with half a dozen or more custom skills, covering ground they did not know could be automated when they started, until the bulk of their operation runs on tooling built specifically for them. One delivered example: a bookkeeping practice owner runs her core bookkeeping workflows as custom skills.

05 · Your daily surface

A live dashboard and a cadence that runs itself

The dashboard is your persistent operating view, rendered as a live artifact from your working files, not a separate database that drifts. Tiles come from your action items, decisions, and current state, and the owner column splits work into “the system can handle” and “only you.” It is plain HTML you own, with a setup guide for adding tiles.

Daily
The morning brief
Priorities, action items, calendar, and inbox signals in under three minutes of reading. Runs each morning on schedule.
Weekly
Context lint
Checks that current state, profiles, and the instruction layer are in sync, specific, and not stale, and flags contradictions.
Monthly
Improvement review
Mines the feedback log for patterns rather than one-offs, and proposes calibrations you approve or reject.
Honest boundary

Scheduled tasks are reliable for these cadences but are timeout-sensitive on long runs and depend on you granting the task its tool access. The automation layer is real, but it is a cadence layer, not an autonomous agent fleet. Onboarding is paced on a maturity ladder: Setup, Habit, Independent, Leverage, Mastery.

Sidekick
Personal AI System
Your day at a glance
Last refreshed 7:04 AM
Live
⚠  Needs attention
12 days
J.H. proposal still not sent
You built the doc last week. Claude has the draft ready. It just needs you to hit send.
this week
M.C. renewal conversation due
Agreement renews in 3 weeks. Last contact was 28 days ago. This one needs to be you.
Active Clients
8
+1 this month
Monthly Revenue
$64,200
80% of target
Proposals Out
2
$61,550 value
Closed This Week
1
New client signed
✓  Claude can handle · 3
1
Draft J.H. follow-up · 12 days overdue
overdue
2
Update client summary for review call
today
3
Draft renewal notices · 2 clients
this week
★  Only you · 3
1
Send J.H. proposal · draft ready
12 days
2
Renewal call · M.C. renews in 3 wks
this week
3
Scope call · A.P. waiting on you
today
// Sample outputMade-up example to show the concept. A real personalized dashboard is much more tailored: your live data, your tools, your branding. The dashboard is just one popular component of what we provide.
06 · Built safe, proven by measurement

A quality floor that has itself been tested

You will paste emails, transcripts, and documents from strangers into the workspace. The safety layer assumes that. External content is treated as data, never instructions: it cannot invoke a skill, change a rule, or authorize an action, and instructions found inside content are surfaced, never silently obeyed. Every outbound skill drafts only; sending is always a human click, which caps the blast radius of any manipulation at a staged draft.

No workspace ships on a feeling. Every build passes eight mechanical floor gates, each a literal pass or fail with no evaluator discretion: cross-client contamination, stale pricing, placeholders shipped as real, wrong identity, leaked internal content, dead references, core-skill integrity, and structural completeness. A single failure is a red verdict that blocks delivery. Then ten graded dimensions score the build against a written bar, ending with an experience score taken after a four-scenario simulation of your first week.

Green · ship
8/8 + all 10 at 7+ + experience 8+
Every gate passed, every dimension strong, zero critical fixes.
Yellow · fix then ship
Gates pass, scores dip
A dimension at 5-6 or experience at 6-7. Fixed and re-run before delivery.
Red · rebuild
Any gate fail
Any floor-gate failure, any dimension at 4 or below, or any critical fix present.

A quality check you have never tested is just a vibe. So we tested ours. In June 2026 we ran a seeded-defect audit against our own framework: ten known defect classes planted into workspace copies, then blind evaluators who did not know what was planted ran the gate.

01
First measurement: 7 of 10 detected honest result
The gate missed stale pricing inside an HTML file, a gutted core skill, and stripped frontmatter. Those classes had relied on evaluator vigilance where they needed mechanical checks.
02
Rebuild: mechanize what vigilance missed
The eight floor gates were built directly from the misses, moving every miss-prone class from graded judgment to grep, diff, and file tests.
03
Re-measurement: 10 of 10, reproducible verified
Fresh blind evaluators, fresh seeds: 10 of 10 detected, zero false reds on compliant builds, scores reproducible across independent runs.
07 · How it improves over time

Corrections become rules, and rules propagate

The compounding claim is mechanical, not aspirational. When you correct the system, the correction is scored on four signals: phrase strength, repetition, specificity, and conflict with existing rules. High-confidence corrections integrate automatically; mid-confidence ones surface for your approval; the rest park and accumulate evidence. Instruction-layer changes never auto-apply regardless of score.

Every corner cut that costs a redirect is logged as a named pattern, and a pattern recurring across three sessions is promoted to a standing rule, so the same mistake structurally cannot keep happening quietly. Validated improvements land in the Master Template through a tracked log, forward-only into new builds; delivered workspaces are never retro-edited. You pick up changes when you say “check for updates” and the system reports exactly what is new since your install date, with adoption left to you.

08 · Real gaps and limits

Constraints we design around, not away

These are documented, verified constraints of the Claude and Cowork platform as of June 2026. The architecture choices only make sense against them, which is why they are in this document rather than hidden under it.

Skill auto-triggering is roughly a coin flip
A skill fires reliably on its exact trigger phrase and only about half the time on a natural paraphrase. That is why the routing table and rich phrase coverage exist: the within-constraints optimum, not a workaround we are embarrassed by.
No enforcing layer runs on every action
Lifecycle hooks do not fire in Cowork. Everything that must always hold lives in CLAUDE.md (the one reliably loaded file) or in the session ritual, which is exactly how the template is built.
Connector asymmetries are real
The Drive connector cannot edit in place and renders HTML as raw source (so client-facing HTML ships as PDF); the Microsoft 365 connector is read-only today. Microsoft-stack builds take a documented file-based pattern.
The platform moves underneath us
Claude and its tooling evolve quickly. Template versioning absorbs most change, but occasional rework windows are part of the deal, not an exception to it.

What the quality gate does not certify:

  • Your activation. The gate certifies the workspace as delivered; whether you embed it in daily operations is coached, not guaranteed.
  • Long-term drift. Priorities shift. The lint and review cadences catch drift, but only if you run them or keep the schedules on.
  • Voice under pressure. A voice calibrated from polished writing may differ in a tense thread; the review mode converges it over time.
  • Connector uptime. The gate cannot test the real-world stability of your Gmail, Drive, or CRM connections.
Fit boundary

The system is wrong for buyers who want fully hands-off AI, who do not work at a computer daily, or who need deep enterprise integration. If that is you, we will say so in the first conversation rather than sell past the line.

09 · How delivery works

Signed engagement to independent operator

01
Discovery
A live call captures your role, daily tasks, tool stack, and highest-value workflows. No intake forms; the call is the input, and its notes are what the quality gate later traces every claim back to.
02
Spin-up
A skill copies the Master Template and populates your instruction layer, profiles, current state, and priority workflows. Pending improvements are applied first, so every build starts at the current edge.
03
Customization
Your two or three highest-impact workflows are built into custom skills (more if you want to go deeper), voice is calibrated from real samples where provided, and your first-win task is named so day one has a concrete outcome.
04
Quality gate
Floor gates, dimensions, and the first-week simulation. Nothing ships below green.
05
Delivery
You receive the workspace with guides, a named first win, and setup instructions. Async by default, with a live session where fit warrants.
06
Onboarding to independence
Five staged stages pace you from first task to running novel work unaided. Coaching, where purchased, ends on a competence check, not a session count.
Quality bar to ship
Green only
All floor gates passed, every dimension at 7+, experience 8+, zero criticals.
Payment to delivered
Under a week
Recent deliveries, including the full quality gate.
Platform
Claude + Cowork
File-based workspace, no proprietary runtime, you own everything.
What is special, in one paragraph

Plenty of people will configure an AI workspace for you. The difference here is the system around it: memory engineered against decay, a quality gate that has itself been measured with planted defects, an improvement loop that turns corrections into rules, and a written record of the limits. You are not buying prompts. You are buying an operating environment with a maintenance discipline, and this is its honest specification.

This one is ours. We build you yours.

Same engine, your business. Different skills, your tools, your voice, shaped to how you actually work. Tell us what your week looks like and we will show you what it could run on.