Creating Instagram Content for the AI, SI, and Agentic Era

Open the native draft studio

Download the resource ZIP and extract it into a new private folder. Open studio.html directly in your browser. Compare the two ten-slide food carousel drafts for Overnight oats assembly. Read AGENT_OPERATING_MANUAL.md and all twenty points in agent-training.json: native CTA/AI, concrete inputs, draft outputs and stop rules. Inspect strategy.json and assign an artifact to each maturity stage. No account or terminal is needed for the studio; do not publish a synthetic fixture.

Expected: The studio shows A/B drafts and a zero-initialized rubric; the content-agent plan has twenty operating points and native CTA/AI boundaries.

Map the visual platform

List Feed, Reels, Stories, carousel, Live, Notes, bio, Highlights, comments, DMs and broadcast channels. Compare personal, creator and business needs; select a food carousel for saveable assembly steps.

Expected: A format/account map supports the home-cook persona.

Observe the audience and distribution

Review two public food posts and current official guidance. Note follower distribution versus Explore/Reels discovery, readable text and a meaningful save use case without inventing universal signal weights.

Expected: Two dated examples and a connected/unconnected distribution sketch exist.

Set a recognizable visual identity

Choose education, demonstration, commentary and culture pillars for the food account. Sketch a palette, type hierarchy and repeatable jar framing that stays readable at 390px.

Expected: Four pillar ideas and a legible style guide exist.

Write a semantic visual hook

Draft WHO + WHAT + WHY + VALUE in the first frame: busy home cook, overnight oats, assembly friction, clear prep sequence. Compare a visual movement hook, a question hook and a before/after hook.

Expected: Three hooks retain the same recipe promise.

Research a real search intent

Write informational, navigational and commercial query examples. Draft a display name, bio and first caption line related to the food topic; observe actual suggestions when available.

Expected: A dated search brief has natural topic terms and no volume fabrication.

Build the ten-layer keyword stack

Map speech, overlays, caption, relevant hashtags, profile, comments, bio link, canonical page, source recipe and structured object. Use only available relevant hashtag capacity after checking the current composer.

Expected: Ten surfaces share the same entities without stuffing.

Compare the same carousel

Open studio.html and compare A/B caption drafts for the same ten-slide carousel. Keep visual promise fixed; add rolled oats, clear sequence and a real question while preserving warmth.

Expected: A/B drafts address the same overnight-oats assembly.

Draft the knowledge-layer caption

Write topic, assembly problem, method, ingredients, steps, caveats and source attribution in caption.md. Do not claim calories or storage duration without checked support.

Expected: A complete caption contains useful context and an honest recipe status.

Plan OCR-readable overlays

Create a slide text list with large labels, high contrast and margins clear of UI overlays. View a draft at phone width and ask someone to identify the ingredients without the caption.

Expected: A human phone-size reading test records what was legible.

Build the ten-slide carousel

Outline hook, problem, concept, method, diagram, common mistake, corrected approach, checklist, companion action and next step. Keep the public recipe sequence native; place pack validation commands in the companion resource.

Expected: Ten complete slide scripts deliver an assembly outcome.

Make a standalone Reel

Storyboard question → answer → explanation → demonstration → next step in 30–60 seconds. Align jar footage, spoken ingredient names and captions; deliver one full answer rather than withholding a payoff.

Expected: A timestamped storyboard matches speech, image and text.

Connect the knowledge chain

Plan five independent food Reels and link them to the carousel, Highlight and full recipe page. Check each can be understood without earlier clips.

Expected: Five self-contained ideas and a next-step map exist.

Use Stories as a living lab

Draft a poll, a behind-the-scenes assembly image and a question sticker. Explain the 24-hour Story lifecycle and route a useful question to a permanent Highlight or corrected carousel.

Expected: A three-part Story plan has a permanent knowledge destination.

Respond and verify community claims

Write replies to ingredient-substitution, missing-step and evidence questions. Classify opinion, anecdote, first-hand test, documented evidence, expert explanation and independently verified result.

Expected: Three response drafts apply a six-level evidence ladder.

Localize and define the food entities

Translate a caption cue or prepare a fluent-review brief. Define rolled oats and overnight oats consistently and retain ingredient names across slide, transcript and glossary.

Expected: Entity definitions and localization checks preserve the same meaning.

Build a food knowledge graph

Connect ingredient → used in → breakfast jar and step → precedes → mixing. Include source recipe and creator attribution; distinguish the method from claimed health benefits.

Expected: A connected graph has grounded entities and no unsupported benefit claim.

Plan the content factory

Derive Reel, carousel, Stories, YouTube explanation, TikTok demo, LinkedIn production case study, X observation and canonical recipe from one source. Show how a nightly B3 segment could supply original footage and questions.

Expected: Eight native outputs share one checked source.

Design the six-version capstone

Draft social, search, explicit-entity, retrieval, agent-card and provenance versions. Keep the recipe topic and audience fixed. Public visuals remain a food sequence; machine cards stay in a companion layer.

Expected: Six versions show additive changes on one recipe topic.

Plan ten experiments and seven audit lenses

In experiments.md define hook, tags, overlay, localization, real-experience evidence, series, carousel, companion action, Story loop and full-stack tests. Review human, platform, search, AI, retrieval, agent and trust lenses.

Expected: Ten controlled proposals and seven review lenses have measurements and limits.

Approve a complete visual package

Review actual photo permissions, recipe status, caption accuracy and machine-readable companion files. Separate current vision/captions from emerging browsing and speculative SI. No fabricated OCR accuracy or AI citation uplift. Review the primary native AI source in AGENT_OPERATING_MANUAL.md. Record documented inputs/outputs, actual account availability (or NOT VERIFIED), a useful native application and a privacy/failure limit. Use this platform’s CTA chain from agent-training.json, rather than importing another platform’s CTA.

Expected: A publication readiness decision names remaining evidence gaps.

Set up the practice folder

Download the resource ZIP at the top of this Build. Extract it into a new folder you own (for example C:\BBBPractice on Windows, or ~/bbb-practice on macOS/Linux). Open a terminal in the extracted folder. Run the version command for your platform. All subsequent commands assume this folder.

Expected: Python reports version 3.10 or newer and the terminal is in the extracted resource folder.

windows

python --version
Get-Location
Get-ChildItem

macos

python3 --version
pwd
ls

linux

python3 --version
pwd
ls

Audit the mechanism and claim ledger

Read mechanisms.md and claims.json. Attach a direct source and date to established claims; distinguish hypothesis from evidence and future SI from deployed features. Edit knowledge.json and rag.jsonl so each answer stands alone with named entities and a source.

Expected: The ledger separates training, retrieval, indexing, context, citation and action; two source-linked chunks stand alone.

Use the readiness calculator

Open studio.html and score each dimension from 0 to 10 with a written reason. Download versions.json and rubric.json; replace the matching extracted files after reviewing them. Leave metrics.json NOT RUN unless you have actual observations. Use this platform’s displayed dimensions: divide by ten times the dimension count, then multiply by 100.

Expected: A downloadable pair and rubric are saved; the score is self-assessment and unrun metrics are explicit.

Hash and lint the reviewed files

Review your changes first. Run the hash command, then lint and score. Inspect report.json. Commands use the current extracted resource folder; PowerShell runs python, macOS zsh and Linux bash run python3. A missing field must be corrected before hashing again.

Expected: HASH PASS and MEDIA PASS appear with exit 0; the readiness score matches the reviewed rubric.

windows

python media_pack.py hash
python media_pack.py lint
python media_pack.py score

macos

python3 media_pack.py hash
python3 media_pack.py lint
python3 media_pack.py score

linux

python3 media_pack.py hash
python3 media_pack.py lint
python3 media_pack.py score

Prove changed bytes and broken content fail

First change versions.json B.topic to a different topic and save it. Run lint and retain MEDIA FAIL with exit 1. Restore the original topic, review all changes, run hash, then lint and retain MEDIA PASS with exit 0.

Expected: A mismatched topic produces MEDIA FAIL; a reviewed correction produces MEDIA PASS.

windows

python media_pack.py lint
# After correcting and reviewing the topic:
python media_pack.py hash
python media_pack.py lint

macos

python3 media_pack.py lint
# After correcting and reviewing the topic:
python3 media_pack.py hash
python3 media_pack.py lint

linux

python3 media_pack.py lint
# After correcting and reviewing the topic:
python3 media_pack.py hash
python3 media_pack.py lint

Run a source-linked retrieval probe

Run the supplied question, then an unrelated query. Inspect the answer and source. This standard-library demo uses lexical word overlap, not embeddings, a vector database or an AI citation measurement. Save actual OS command/exit/output and mark other OS branches unverified.

Expected: The relevant query returns source-linked chunks; the unrelated query abstains. The source label names the synthetic course draft, not Instagram’s ranking article as a recipe authority.

windows

python media_pack.py retrieve --query "How can an overnight oats carousel remain understandable outside its caption?"
python media_pack.py retrieve --query "quasar waffle weather"

macos

python3 media_pack.py retrieve --query "How can an overnight oats carousel remain understandable outside its caption?"
python3 media_pack.py retrieve --query "quasar waffle weather"

linux

python3 media_pack.py retrieve --query "How can an overnight oats carousel remain understandable outside its caption?"
python3 media_pack.py retrieve --query "quasar waffle weather"

Record provenance and a human approval decision

Use provenance-notes.md to record author, capture/source dates, rights, AI assistance and unresolved claims. SHA256 detects byte changes but does not sign the file or prove truth. Read the source/command cards, review the native capstone and export course evidence. Actual publication requires your own account, current rules and a human decision.

Expected: The handoff includes native drafts, source/rights review, unsigned integrity manifest, explicit live-status limits and an approval decision.

Write a repeatable onboarding checklist

Fill in onboarding-checklist.md for your agent. Record AGENTS.md, the tool’s user settings and memory folder, the assigned workspace, permissions, guard location, backup schedule, and a final proof task. Keep the checklist in your project.

Expected: The checklist contains a concrete path and owner for rules, memory, permissions, guard, backup, restore and final verification.

Demonstrate the variable-path limit safely

Run workspace_guard.py --self-test. Read the source: the target is resolved before deciding. The variable_target case points at the home folder but performs no filesystem operation. Compare this with a hook that sees only command text.

Expected: GUARD PASS reports inside allowed and profile, outside, variable-derived profile and workspace root denied; no deletion was executed.

windows

python workspace_guard.py --self-test

macos

python3 workspace_guard.py --self-test

linux

python3 workspace_guard.py --self-test

Verify the actual protection in your tool

For CLI tools, open the hook/permissions screen and confirm the configured guard is active. Use your tool’s documented pre-command hook protocol; inspect workspace_guard.py from the resource pack; it is a demonstration, not an installed CLI hook. Run a harmless directory listing, then a guard dry-run targeting the profile. Do not execute a destructive profile probe. If you use a hosted agent, do not assume a local shell hook protects its remote computer: use project-only tasks and reviewed actions, with backups. If no agent is used in this course, record the demonstration only. A hook is active only after a real tool-specific refusal test; otherwise record NOT INSTALLED with the reason.

Expected: A harmless command runs, the guard dry-run returns DENY, and the checklist records the actual hook protocol and active state or the Grok Bot limitation.

windows

python workspace_guard.py --self-test
python workspace_guard.py --target "$env:USERPROFILE"

macos

python3 workspace_guard.py --self-test
python3 workspace_guard.py --target "$HOME"

linux

python3 workspace_guard.py --self-test
python3 workspace_guard.py --target "$HOME"

Enable a real backup of memory and project files

Connect a second backup drive. Windows: configure System Protection as additional recovery and use a scheduled copy/File History that explicitly includes hidden agent folders. macOS: configure Time Machine and verify dot folders are included. Linux: use a home backup such as restic/Deja Dup; Timeshift omits /home by default. Download the copy-only profile backup script for your platform, inspect it, and adapt the folder list to your tool. Record the last successful scheduled run; protect backup access because it may contain credentials. On Windows, review the script, unblock only that downloaded file, then run it with the shown process-only RemoteSigned policy. Group Policy can still refuse it; report that limitation without changing machine policy.

Expected: A backup on another drive includes the tool’s user settings and memory folder and this project, and a successful schedule/time is recorded.

windows

# Read the extracted script before unblocking this single file.
Get-Content .\profile-backup.ps1
Unblock-File -LiteralPath .\profile-backup.ps1
powershell.exe -NoProfile -ExecutionPolicy RemoteSigned -File .\profile-backup.ps1 -Destination D:\Backups\llm-profiles

macos

bash profile-backup.sh /Volumes/YourBackup/llm-profiles

linux

bash profile-backup.sh /media/YourBackup/llm-profiles

Practice a hash-verified restore

Run restore_drill.py with a separate backup directory. The script creates a new proof file, copies it, restores a second copy, and compares SHA256 hashes. Then restore one non-secret file from your actual agent memory backup into a separate scratch directory and open it; do not overwrite the live profile.

Expected: RESTORE PASS contains matching hashes; the actual memory file is readable after restoration into scratch.

windows

python restore_drill.py --backup-root D:\Backups\bbb-practice --work-root practice

macos

python3 restore_drill.py --backup-root /Volumes/YourBackup/bbb-practice --work-root practice

linux

python3 restore_drill.py --backup-root /media/YourBackup/bbb-practice --work-root practice