Creative workflow
Request → triage → brief → production → internal review → partner approval → export/delivery → performance feedback.
01 · Purpose
What Atlas is
Atlas is Exactius’s shared context agent for the Omaze DE partner lane. Its job is to keep operational context connected, traceable and reusable across the team.
It reads approved shared sources, links evidence to the relevant house and campaign phase, and maintains a curated context layer. That lets it answer factual workflow questions without asking everyone to retell the story.
Atlas is designed for operational clarity: finding, tracking, naming, exporting, notifying and summarising. It is not a creative director, reviewer or decision-maker.
Evidence before interpretation
Atlas should show where a claim came from and distinguish confirmed status from a comment, signal or inference. If a source is missing, it should say so.
02 · Current understanding
What Atlas understands today
The current context is specific to Omaze DE Creative—not a general archive of every Exactius or Omaze project.
Campaign structure
Launch, BV/bonus phases, Early Close, Close, Big Swings and ongoing/evergreen work, linked by house.
Creative outputs
Static, video, copy and concept work across Meta and secondary channels, with documented naming conventions.
Live house hubs
Current operational hubs for H5, H6 and H7 with linked tasks, assets, stages, pending approvals, deadlines and recent mentions.
Source authority
Which source answers which question—for example, ClickUp for task stage and Figma comments for static-review evidence.
Campaign memory
Stable workflow facts, source documents, meeting operations, action-item candidates and curated learnings with supporting data.
03 · Connected systems
Access today, with the real limits
“Connected” does not mean “everything in the system.” Atlas can only read the accounts, channels, files and projects that are authorised and shared with it.
ClickUp
Live nowReads the Omaze DE Creative Pipeline, OM Timeline and live static/video naming documentation. Can check tasks, owners, due dates and stages.
Boundary: ClickUp is authoritative for task status. Atlas does not create, edit, assign or close tasks.
Slack
Live nowScheduled ingestion reads four approved shared/project channels, applies a DE filter and surfaces operational requests with message evidence.
Boundary: Slack messages are signals, not canonical task status. DMs are excluded from shared-context ingestion.
Figma
PartialReads 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.
Frame.io
Live nowRead 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.
Google Workspace
PartialAuthenticated Drive/Docs access for files shared with Atlas, including the Creative source map and H6/H7 narratives.
Gap: The Big Swing deck, copy working sheet, H7 copy matrix and Creative-call notes are not shared; the H6 matrix link is broken.
Fireflies
Live nowReads 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.
GitHub + context vault
Live nowA 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.
Cloudflare Pages
Live nowCan publish approved static artifacts to isolated exactius-* Pages projects after a content and secret scan.
Boundary: Pages links are public. The protected apex and www sites are not touched.
Source hierarchy matters. If Slack says “approved” but ClickUp still says “in partner approval,” Atlas should flag the conflict—not silently overwrite the ClickUp status.
04 · Practical use
What the Creative team can ask right now
Good requests have a house, phase, task, channel or time window. Atlas can still help when those are missing, but it will label uncertain links rather than guessing.
01
Find assets and source documents
Ask for the ClickUp task, Figma frame, Frame.io asset, narrative or naming source for a house/phase. Atlas can return the best available links and call out missing access.
02
Check task and campaign status
Request a house or phase roll-up, open tasks, due dates or recent stage changes. The answer should be anchored to current ClickUp evidence.
03
Track approvals and exceptions
Surface assets in partner approval, candidate approval language, unresolved review exceptions and conflicting signals. Comment-derived approvals stay labelled as candidates until stronger status evidence confirms them.
04
Catch operational requests
Atlas scans approved shared Slack channels, matching Fireflies meetings, Figma comments and Frame.io comments for explicit asks or commitments. It checks for an existing ClickUp task before surfacing new work.
05
Draft controlled ClickUp-task candidates
Atlas can prepare a paste-ready title, description and evidence link, deduplicated against the pipeline. A human decides whether it becomes a real task.
06
Prepare briefs and status reports
Combine current source links into a concise brief, daily status, meeting pre-read, handoff or “what did I miss?” summary. Missing sources and conflicting evidence remain visible.
07
Maintain campaign memory and learnings
Preserve stable workflow context and evidence-backed learnings across weeks. Learnings follow a structured method and should not appear without supporting data.
08
Connect activity to performance context carefully
Atlas can line up what was made, when it changed, what test was intended and what performance data was reported. It can describe associations and test evidence; it cannot prove causality unless the source and test design support it.
05 · Human judgment
What Atlas should not be used for
Atlas is operational and evidence-led. The Creative team retains creative judgment, partner judgment and accountability.
Do not use Atlas to…
- Decide whether creative is “good,” on-brand or visually strong.
- Give legal, compliance, T&C or partner approval.
- Prove that a creative change caused a performance result without valid evidence.
- Replace ClickUp as the source of task status.
- Ingest or quote Slack DMs into shared context.
- Assume access to an unshared deck, sheet, file or channel.
- Modify ClickUp or Frame.io records.
Human approval is required for…
- Creative direction and quality decisions.
- Promoting a task candidate into ClickUp.
- Partner, legal and compliance sign-off.
- Resolving ambiguous market, naming or approval signals.
- Sharing sensitive material or publishing anything publicly.
- Acting on a performance interpretation or test recommendation.
- Adding new sources, channels or access permissions.
06 · The difference
Atlas versus Claude on a personal computer
Both can help write and reason. Atlas’s advantage is controlled shared context—not a “smarter chatbot” claim.
| Area | Atlas | Personal Claude |
|---|---|---|
| Context | Uses the team’s curated Omaze DE context and approved live sources. | Usually knows only what you paste, upload or connect in your own session. |
| Continuity | Maintains shared house hubs, action candidates, meeting operations and learnings over time. | Personal conversation continuity; not automatically the team’s shared operational memory. |
| Evidence | Designed to link claims to task, comment, meeting or source evidence and label uncertainty. | Can cite uploaded material, but the user must supply and maintain the source set. |
| Live status | Can read approved operational sources; ClickUp remains authoritative. | Cannot know current team status unless connected or given an export. |
| Automation | Runs scheduled, scoped ingestion and status workflows for Omaze DE. | Primarily user-driven unless separately configured. |
| Team boundaries | Shared-channel-only ingestion, DE filtering, no ClickUp mutation, read-only Frame.io workflow. | Depends on each person’s account, prompts and local setup. |
| Best fit | Shared operational context, retrieval, traceability, pre-reads and campaign memory. | Personal drafting, exploration and work with files you choose to provide. |
07 · Capability map
Live now, partial and future potential
| Capability | State | What that means |
|---|---|---|
| ClickUp status and deadline checks | Live now | Reads the DE Creative Pipeline and OM Timeline; ClickUp is the final authority. |
| Shared Slack request detection | Live now | Four approved shared/project channels are monitored with DE filtering. DMs are excluded. |
| Figma review evidence | Partial | H7 pages/comments and H6 comments are readable; H6 full export and earlier performance-file links are missing. |
| Frame.io asset and comment retrieval | Live now | Omaze DE folders, files and authored comments are readable. Atlas does not write or set approval state. |
| Google narratives and source docs | Partial | Shared Docs are readable; several decks and copy sheets are blocked or incorrectly linked. |
| Meeting action capture | Live now | Available Fireflies transcripts are scanned against the Creative meeting guide for operational asks and commitments. |
| House/phase operational memory | Live now | H5–H7 hubs connect tasks, assets, approvals, deadlines, mentions and evidence. |
| Draft ClickUp-task candidates | Live now | Atlas drafts and deduplicates candidates. Humans promote them; Atlas never creates the task. |
| Curated learnings and performance context | Live now | Uses structured learnings rules and available reported data; avoids unsupported causal claims. |
| House/phase/format performance querying | Partial | The dedicated Violet comparison query path is not connected, and DE performance-file keys are incomplete. |
| Complete copy and Big Swing context | Partial | Blocked Drive items prevent complete coverage until files are shared and broken links are corrected. |
| Human-approved task creation workflow | Future | Potential only after governance and explicit approval controls. It is not available today. |
| Broader Creative source coverage | Future | Could expand when additional files, channels and formal approval signals are deliberately shared. |
08 · Start here
Example prompts to try
Copy one, then replace the house, phase or date range. Atlas should answer with links and flag missing evidence.
“Give me the current H7 BV3 Creative status: tasks, stages, partner approvals, exceptions and the next deadlines. Link every source.”
Status roll-up“Find the source task and review links for the H7 BV2 Value Count-up video. Tell me what is confirmed versus comment-only.”
Asset retrieval“What Creative requests appeared in approved Slack channels, Fireflies, Figma or Frame.io this week that are not already covered by ClickUp?”
Request detection“Draft a ClickUp-task candidate for this request. Check for duplicates first and do not create or modify any task.”
Controlled drafting“Prepare a five-minute pre-read for the next Creative status meeting: changes since the last meeting, pending approvals, deadlines and blockers.”
Meeting pre-read“I was away for three days. Summarise what changed in Omaze DE Creative, grouped by house and phase, with source links and unresolved conflicts.”
Missed context“Show the available evidence connecting the latest Creative activity to reported performance. Separate observation, test result and unsupported causality.”
Performance context“Which Creative source documents are accessible for H6 and H7, and which expected files are still blocked or incorrectly linked?”
Access checkHow this guide was checked. Capability claims were reconciled against the live Creative Lane documentation, source-access matrix, current H5–H7 hubs, action-candidate ledger, scheduled workflow state and direct integration checks. Access can change; Atlas should re-check the source before giving a time-sensitive answer.