Do and verify the work
Atlas gathers evidence, completes the request, and checks the real result before treating the approach as proven.
Atlas brings together Creative operations, assets, team knowledge and current performance data. Ask a question in normal language and it can investigate the evidence, explain what matters, and turn the result into a useful report, deck or next step. Because Atlas is available in Slack, you can ask from your phone and its online working environment can do the real work while your computer is closed.
Message it in Slack from desktop or mobile. Atlas can find the relevant assets, query current data, compare like with like, and produce the answer or deliverable without depending on your computer staying open.
Atlas is a deeply informed digital teammate: an agent that retains rich operational context and can use it to help the team understand what is happening, decide what to do next, and move work forward.
It connects knowledge across approved shared sources, keeps that understanding current, and turns context into practical action. Atlas can answer questions, generate reports, analyse patterns, execute tasks across platforms, build automations and workflows, and create or run reusable skills.
Atlas is not limited to the Creative lane as a product vision. Omaze DE Creative is its current proving ground, while the longer-term goal is to support people and workflows across the wider team.
Atlas combines persistent team knowledge with execution. It should ground its work in evidence, show what it used, verify consequential actions, and continuously improve how it works.
Atlas is powered by the Hermes self-improvement loop. It can turn a proven process, or a correction from the team, into a reusable skill rather than relearning the same workflow in every conversation.
Atlas gathers evidence, completes the request, and checks the real result before treating the approach as proven.
It records the procedure, required sources, permissions, approval gates, verification steps and known pitfalls in an Atlas skill.
If Atlas gets something wrong, a teammate can correct it. If someone has useful context that Atlas does not yet know, they can share it directly in the conversation. Atlas can store durable, relevant context so it is available to the team in future interactions.
Future sessions can use the updated context and load the improved skill. Atlas preserves the useful correction or new information instead of forcing the team to explain it again.
A skill can be run on demand or connected to a scheduled task or event-driven automation. Creating the skill does not automatically schedule it or grant permission to write to external systems.
Stable facts, preferences, access details and standing boundaries.
Shared operational knowledge, decisions, source maps, campaign context and evidence. Authorised teammates can add or correct durable context through normal conversation.
Reusable execution playbooks describing how Atlas performs a specific workflow safely and consistently.
Approved skills connected to schedules or events so useful workflows can run reliably for the team.
You do not need to edit a database or write a special document. Tell Atlas what it got wrong, explain a missing piece of context, or give it a source to ingest. Atlas can preserve durable information for future use while distinguishing a teammate’s contribution from independently verified source evidence.
Describe the workflow in normal language. Atlas can inspect related Cowork skills, n8n workflows and existing Atlas capabilities, propose a safe design, build it, dry-run it, and separately ask before enabling automation or consequential writes.
These are team-specific capabilities built around real Exactius workflows, not generic chatbot features.
Pulls Creative activity from approved operational sources, updates house hubs, links evidence, detects action candidates and produces status updates.
Purpose: Keep the Omaze DE Creative operating picture current without manually assembling every source.
Turns weekly decks and meeting transcripts into structured learnings, a learning agenda and a testable roadmap with evidence requirements.
Purpose: Preserve what the team is learning, not just what happened.
Copies approved final copy from a working Google Doc into the original CRM strategy brief while preserving its tabs, tables and wireframes.
Safety: Runs a structural dry-run and requires approval before writing.
Answers detailed Creative questions and wider Omaze DE performance questions using current data and the business context needed to interpret it properly.
Useful for: Creative rankings, house and phase comparisons, fatigue checks, channel movement and commercial performance reviews.
Reads existing n8n workflows and Cowork skills, understands their intent and dependencies, and adapts approved workflows into Atlas skills and automations.
Purpose: Reuse good work instead of rebuilding the process from scratch.
Combines analysis, operational context, source material and narrative into polished reports, presentations, dashboards and shareable pages.
Strength: Atlas can research and reconcile the material before it designs the final output.
The current context is specific to Omaze DE Creative—not a general archive of every Exactius or Omaze project.
Request → triage → brief → production → internal review → partner approval → export/delivery → performance feedback.
Launch, BV/bonus phases, Early Close, Close, Big Swings and ongoing/evergreen work, linked by house.
Static, video, copy and concept work across Meta and secondary channels, with documented naming conventions.
Current operational hubs for H5, H6 and H7 with linked tasks, assets, stages, pending approvals, deadlines and recent mentions.
Which source answers which question—for example, ClickUp for task stage and Figma comments for static-review evidence.
Stable workflow facts, source documents, meeting operations, action-item candidates and curated learnings with supporting data.
Who team members are, their responsibilities, the workstreams they support and identity details needed to avoid mixing up similarly named people.
What each recurring meeting is for, which topics belong there, who participates and how decisions or actions should flow into the wider operation.
Creative naming conventions, house and phase codes, workflow terminology and the source documents that define how work should be classified.
“Connected” does not mean “everything in the system.” Atlas can only use the accounts, channels, files, projects and write permissions that are authorised and shared with it.
Has normal-user access as Atlas. It can read, create, edit, assign, move and close tasks, and add comments across the authorised workspace.
Boundary: ClickUp remains authoritative. Atlas should confirm consequential or ambiguous changes before writing, then read the task back to verify the result.
Talk directly to Atlas from Slack on desktop or mobile. Ask a question or request real work, and Atlas can investigate, update a report or deck, and deliver from its own online working environment while your computer is closed.
Boundary: Slack messages are signals, not canonical task status. DMs are excluded from shared-context ingestion.
Reads shared Omaze DE house-file comments with author, time and node context. H7 pages/comments are available; H6 comments are available.
Gap: H6 full-file export is blocked, and performance-file keys for earlier houses have not been supplied.
Read access to the Omaze DE project, including folders, files and authored comments. Asset paths can be linked to tasks and house hubs.
Boundary: Read-only. Comment language is evidence; formal approval logic is not assumed where the source does not prove it.
Authenticated access to the shared Creative source set, including the source map, H6/H7 narratives, H6 Big Swing deck and H6/H7 messaging matrices.
Verified: Shared Drive discovery, metadata and export now work correctly. A separate copy-working document still needs a canonical link, and the Gemini Creative-call notes remain unshared.
Reads meeting transcripts and filters them against the documented Creative meeting guide to capture asks, commitments and asset mentions.
Boundary: Only available transcripts and matching meetings can be used. Atlas separates operational actions from learnings.
Answers questions across Creative assets, spend, revenue, conversions, CAC, ROAS, houses, events, channels, CRM, cohorts and LTV.
Strength: Atlas uses current data together with house-cycle, attribution and operational context so the answer is useful, not just numerically correct.
A Git-backed, curated context vault holds source summaries, house hubs, action candidates, meeting operations and learnings with evidence links.
Boundary: It is a curated layer, not a raw mirror of every message, comment or transcript.
Can design, build and maintain scheduled tasks, event-driven automations and reusable workflows that operate across authorised platforms.
Default: Atlas should define the trigger, permissions, approval gates, verification and delivery clearly before enabling a workflow.
Can read Exactius n8n workflow definitions and execution history to understand existing triggers, node logic, mappings and platform dependencies.
Boundary: n8n is source material for porting. Atlas rebuilds approved workflows as scheduled tasks and automations rather than treating n8n as the default runtime.
Can read the private Exactius/cowork-plugins repo and use its user-created skills as source material for new Atlas capabilities and automations.
Boundary: Preserve the skill’s intent, safety rules and judgment. Port it into Atlas/Hermes rather than silently changing behavior.
Can publish approved reports, dashboards and static artifacts as either public links or secure Exactius pages protected by email one-time PIN access.
Choice required: Atlas confirms public versus secure before publishing. Secure pages use an approved email/domain allowlist and have no public origin bypass.
Start with the question you need answered. Atlas can locate the relevant work, query the current data, compare the right periods and explain what the evidence means.
Locate the relevant ClickUp tasks, Figma frames, Frame.io assets, documents, meetings and team discussions, then explain what changed and what remains unresolved.
Compare videos, static assets, messages and treatments using delivery scale, spend, FTBs, CAC, ROAS and LTV. Separate high-volume winners from efficient small samples and include preview links.
Compare the current house or BV with equivalent stages from previous campaigns, accounting for duration, spend, house-cycle position and other differences that would make a simple calendar comparison misleading.
Check whether performance movement looks like fatigue, weak delivery, audience or channel mix, campaign timing, attribution restatement or an early sample that needs more time.
Analyse visual treatment, prize composition, urgency, layout, copy combinations, influencer content and video type, with the paired evidence needed to support each pattern.
Check a deck against current data, reconcile the arithmetic, add missing context and turn unsupported conclusions into clearer findings and testable next steps.
Combine live performance, historical context, assets, team learnings, tasks and decisions into a polished Creative review, campaign retrospective, client presentation or pitch deck.
Create a pre-read or decision brief showing what changed, what the data says, the strongest examples, open questions, dependencies and the decisions required from the room.
Use Slack on your phone to request an answer, Creative analysis, report update, deck edit or follow-up. Atlas has its own online working environment, so the work does not depend on your computer being open.
Turn an approved recommendation into a ClickUp update, task draft, team handoff or follow-up report, then verify the saved result instead of leaving the insight stranded in a chat.
Turn a repeatable review, status check or reporting process into a shared skill or scheduled workflow so the team receives the same quality of analysis consistently.
Claude is a powerful personal collaborator. Atlas is a context-rich team collaborator that can research, analyse, create and deliver from information already connected to it.
| Area | Atlas | Claude on your computer |
|---|---|---|
| Starting point | Begins with the team’s shared context, connected sources and current work. | Begins with the conversation, files, project and services available in that person’s session. |
| Data questions | Can retrieve the relevant business meaning, query current data, check the result and explain the commercial decision it supports. | Can analyse powerfully when the user supplies or connects the right data and explains the needed context. |
| Creative context | Already connects assets, tasks, campaigns, meetings, approvals, performance and prior learnings across the team. | The user normally gathers and introduces the relevant material for that piece of work. |
| Reports and decks | Can research, reconcile and analyse the material before producing a comprehensive report, dashboard or pitch deck. | Excellent for drafting and design from the material available in the local session. |
| Collaboration | Multiple teammates can use and improve the same shared understanding and reusable capabilities. | Primarily supports the individual operating the local session. |
| Availability | Reachable through Slack on desktop or mobile. Atlas’s own online working environment stays available and can continue the requested work without relying on the requester’s computer. | Usually depends on the individual’s computer, active session and the connections available there. |
| Continuity | Retains useful team context, corrections and workflows across sessions. | Continuity depends on that user’s projects, sessions and setup. |
| Moving work forward | Can connect the result to shared tasks, reports, follow-ups and recurring workflows. | Best suited to interactive personal work unless the user separately shares or operationalises the result. |
Use Claude locally for exploration, drafting, coding and focused personal work. Use Atlas when the answer should draw on team context and current data, become a shared report or deck, or continue moving after one person closes their computer. Message Atlas in Slack from your phone and ask for the answer or the finished work.
| Capability | State | What that means |
|---|---|---|
| Creative operational context | Live now | Connects tasks, assets, reviews, approvals, deadlines, meetings and team requests with source links. |
| Creative performance analysis | Live now | Compares Meta ads and banners by asset, format, theme, house and campaign phase using delivery, conversion, CAC, ROAS and LTV evidence. |
| Broader Omaze DE analysis | Live now | Answers wider questions across spend, revenue, channels, platforms, houses, events, CRM, cohorts, subscriptions, cross-sell and attribution. |
| Creative fatigue and repeat analysis | Live now | Separates scale from efficiency, checks sample strength and investigates competing explanations before recommending what to repeat or test. |
| House-wrap and deck review | Live now | Reconciles presentation claims with current data, source material, attribution and campaign-stage context. |
| Comprehensive reports and pitch decks | Live now | Creates polished Creative reviews, retrospectives, pre-reads, dashboards and shareable presentations from context plus current data. |
| ClickUp work management | Read + write | Can find, draft, create and update work with confirmation and saved-result verification where needed. |
| Figma review evidence | Scope varies | Reads authorised files and authored comments where the connected account has access. |
| Frame.io asset and comment retrieval | Live now | Finds authorised video assets, folders and authored comments and connects them to the wider workflow. |
| Meeting and deck learnings | Live now | Turns approved meeting and deck evidence into structured learnings, hypotheses and next checks. |
| Scheduled reviews and reporting | Live now | Can run approved recurring checks and reports with clear delivery and verification. |
| Broader team and partner coverage | Expanding | The same approach can extend as additional partner context, sources and team workflows are deliberately onboarded. |
Atlas grows around real team needs. If you have a repetitive task, a report you wish existed, a source that is hard to search, a workflow that keeps breaking, or an idea for how the team could work better, bring it to the R&D team. We can explore it with you and build the right capability into Atlas.
Describe the outcome you want. You do not need to know what the technical solution should be.
Show the R&D team the manual steps, duplicated work or recurring handoff that consumes your time.
Suggest a system, document set or data product that would make Atlas’s context, analysis or execution more useful.
We can explore the value, access, safety and effort with you before deciding how to build it into Atlas.
Start with “I wish Atlas could…” or “Our team needs help with…” and bring that need to R&D. We will work with you to understand the workflow, investigate what is possible and build the strongest ideas into Atlas as new context sources, skills, reports, dashboards or automations.
Ask the real question. Add the house, BV, comparison period or intended audience when you know it, and Atlas can establish the rest from the connected context and data.
“Which H7 BV videos are worth repeating? Compare scale, FTBs, CAC and LTV, include preview links, and separate strong evidence from small samples.”
Repeat decision“Compare H7 static Creative with the previous three houses at equivalent campaign stages. Explain which themes and treatments performed differently and what we should test next.”
House comparison“Investigate whether these assets are showing Creative fatigue. Check delivery, frequency, audience and channel mix, campaign stage, recent performance and sample strength before concluding.”
Fatigue investigation“Review this house-wrap deck against the current data. Correct the arithmetic, attribution and unsupported conclusions, then suggest clearer findings and next tests.”
Deck review“Create a comprehensive Creative performance report for the last complete house cycle. Combine live data, assets, team learnings, operational movement and the decisions needed next.”
Creative report“Build a client-ready pitch deck showing the strongest Creative learnings, current performance evidence, representative assets and the next opportunities.”
Pitch deck“Prepare a five-minute pre-read for tomorrow’s Creative meeting: what changed, what the data says, the strongest asset examples, open questions and decisions required.”
Meeting pre-read“Find the source tasks, Figma frames and Frame.io assets for H7 BV3, then connect each item to its current status and available performance evidence.”
Asset and status map“Analyse which visual, messaging and format themes separate the strongest and weakest H7 static assets. Keep the paired spend, FTB and CAC evidence with each finding.”
Theme analysis“Turn the approved recommendations from this analysis into proposed ClickUp follow-ups with evidence, ownership and next checks. Show me the drafts before creating anything.”
Analysis to action“I’m away from my computer. Review the current house-wrap deck against the latest data, correct weak claims, and prepare the updated version for review.”
Mobile Slack work request“Create a recurring weekly Creative review that combines status, new learnings and material performance movement, and only surfaces items that need the team’s attention.”
Recurring review