SocialSeed.ing — By Agent · console

lead agent online · 5 sub-agents · ADK / A2A / MCP on Vertex
campaign GlowSerum launch budget cap $2,000.00 spent $1,463.21 verified views 146,321 live CPV $0.0100 state running · monitoring
SS
lead agent
Tell me what you're launching and your budget — one sentence is enough. I'll plan the seeding push and run it.
YOU
you
launch a TikTok + Shop seeding push for our new GlowSerum, $2k hard cap, target US 22–34 skincare.
SS
lead agent
Got it. Decomposing into a 5-agent plan and spinning up the team now. You'll see them work in the trace pane →

campaign plan

  • Strategist — audience + hook angles, GMV target
  • Sourcing — shortlist micro-creators (mock TikTok graph)
  • Content — AI briefs + captions w/ mandatory #ad disclosure
  • Publisher — schedule & post via mock TikTok Shop API
  • Analytics — verified-view metering, fraud filter, reallocation
Guardrails armed: hard_budget_cap $2,000 · fraud_filter (dedup + watch-time ≥ 2s + source-anomaly + attribution) · disclosure_check on every brief.
SO
sourcing agent → asking you
I found 3 creator tiers in the mock graph. I recommend the mid-tier shortlist (18 creators, est. 92–160k views) — best predicted CPV. Want me to lock that, widen to include nano-creators, or show you the list?
Approve mid-tier shortlist Widen + add nano Show me the 18
YOU
you
approve mid-tier.
CO
content agent
Drafted briefs for all 18. Sample brief — review or edit by chat:

creator brief · @skinwithmara

Hook (0–2s): "I stopped using 4 serums for this one."

Storyboard: dewy-skin morning routine → dropper close-up → 12-hr glow check → Shop pin tap.

Caption: "okay the glow is unreal 🫧 linked in my Shop — #AD · paid partnership w/ GlowSerum"

disclosure_check: PASS — #ad + branded-content label required at publish.

Approve all 18Edit hook by chatRegenerate softer tone
YOU
you
approve all 18, go live.
PU
publisher agent
Scheduling 18 posts across 6 days via mock TikTok Shop API. 17 accepted, 1 retry (rate-limit) → recovered. All live. Handing the campaign to Analytics for metering.
AN
analytics agent · streaming
Verified-view meter is running. Billing at $0.01 / verified view, fraud filter active:
146,321 verified views
raw views ingested171,940
– 19,402 dedup / bot-clusterrejected
– 6,217 watch-time < 2srejected
billable spend$1,463.21 / $2,000.00
Shop click-throughs5,108
attributed orders / GMV214 · $9,630
I'm reallocating spend: pausing 4 underperformers, scaling @skinwithmara + 2 others. I'll auto-stop when billable spend hits the $2,000 cap and send you the ROI wrap-up.
SS
lead agent
Strategist is reviewing mid-campaign performance…
— you are caught up · the agent will message you when the budget cap is reached —
live agent trace · A2A handoffs + MCP tool calls
Lead Agent · orchestrator
gemini-2.x on Vertex · deployed on Agent Engine
Parsed brief → "GlowSerum launch / $2k / US 22–34 skincare". Built plan, armed guardrails, fanned out to 5 sub-agents.
→ A2A: dispatch(plan) to Strategist
Strategist Agent
audience modeling · GMV target
3 hook angles ranked; predicted blended CPV $0.0098; GMV target $8–11k @ $2k spend.
mcp.trends.query(niche="skincare", geo="US")200 ok
MCP server: mock-tiktok-trends
→ A2A: handoff(audience_profile + angles) to Sourcing
Sourcing Agent
creator graph traversal
mcp.creators.search(tier="micro", geo="US", topic="skincare")200 · 1.4k hits
mcp.creators.score(ids=[…], model="cpv_predict")200 ok
MCP server: mock-tiktok-graph
3 tiers built. Paused for human approval → user picked mid-tier (18 creators).
→ A2A: handoff(shortlist_18) to Content
Content Agent
brief + caption generation
18 briefs generated; ran disclosure_check on each — all PASS (#ad + branded-content label enforced).
guardrail.disclosure_check(briefs=18)18/18 pass
→ A2A: handoff(approved_briefs) to Publisher
Publisher Agent
scheduling via mock Shop API
mcp.tiktok_shop.schedule(post, when=…) ×181 × 429 rate-limit
retry post#12 after backoff201 created
MCP server: mock-tiktok-shop
→ A2A: handoff(live_post_ids) to Analytics
Analytics Agent · running
verified-view metering · reallocation loop
mcp.metrics_sim.poll(post_ids)streaming…
guardrail.fraud_filter(raw=171,940)→ 146,321 verified
MCP server: metrics-simulator
Billable spend $1,463.21 / $2,000. Reallocating: pause 4, scale 3. Watching cap.
→ A2A: report(perf_snapshot) to Strategist · ⟳ loop
Guardrail · hard_budget_cap
armed — fires at $2,000.00 billable
⏸ will halt Publisher + Analytics spend, then emit ROI wrap-up to chat.