Agents

PulseAd is run by agents at three layers. A new product leader should hold this shape before the details:

1. In-app agents — the 11 agents a user opens in the Pulson app under /agent/..., grouped into Planning, Reporting, and Campaign.
2. The chat engine — when a user talks to Pulson, a graph of agents (router → specialist → composer) answers, in ai-api.
3. Autonomous back-office agents — 18 scheduled/orchestrated agents in pulsead-agents that monitor accounts, rebalance budgets, and run keyword automation, mostly on cron — these power what the in-app agents display. (Down from 21 after the legacy weekly-report LLM pipeline — 4 agents — was deleted 2026-06-25; up by a new single-agent support-reminder job added 2026-08-06. See What’s deprecated.)

Two facts that cut across everything:

• Models split by service. ai-api (chat, reports) runs on OpenAI GPT‑5 family models. pulsead-agents (autonomous) runs on AWS Bedrock — Claude Haiku 4.5 by default, Claude Sonnet 4.6 for the writer/decision agents. The Snowflake semantic layer’s Cortex Agent also uses Sonnet 4.6.
• Reads are free; Amazon writes are hard-gated. Real Amazon Ads budget/bid writes are gated to a single pilot brand (KISS) today, and every write path is behind approval or an explicit auto-approval toggle. See Capabilities.

1. In-app agents (what the user sees)

Eleven agents, in three families. “Default” is whether it’s on for a brand without any setup.

Agent	Family	Reads	Can change Amazon?	Default
News & Market Intelligence	Planning	Exa.ai news/search (8 marketplaces)	No	Off (per subscription)
Pulson Weekly Report	Reporting	Snowflake performance (ops-curated/published)	No	Active (managed tier)
Weekly Report Generator	Reporting	Snowflake performance	No (suggestions only)	Active
Monthly Report Generator	Reporting	Snowflake performance	No (suggestions only)	Active
Daily Brief Generator	Reporting	Snowflake performance	No (suggestions only)	Active
Overview Dashboard	Reporting	Snowflake performance (KPIs, trends, product deltas)	No	Active
Event Monitoring	Reporting	Amazon event-window performance by country	No	Active
AMC Builder	Campaign	Amazon Marketing Cloud	No (read-only)	Active
Campaign Optimizer	Campaign	Ads campaign structure/metrics	Yes — propose → chat-approve	Active
Keyword Optimizer	Campaign	Search Query/Search Term performance	Yes — propose → chat-approve	Active
Budget Automation	Campaign	Snowflake pacing/targets	Yes — autonomous under policy	Off (until a cycle runs)

All 11 are defined in one registry (pulsy-frontend/src/core/agent/agent-registry.ts).

Two Planning agents were mocks, and are gone

The registry used to also list Biweekly Marketing Proposal and Product Discovery under Planning. Both were mock agents with no real backend — PR #261 (2026-07-01) hard-deleted their routes, panels, and fixtures; the commit message states Planning’s only remaining live agent is News & Market Intelligence. Keyword Optimizer is not a renumbering trick either: it shipped as “Keyword Discovery” under Planning on 2026-06-30, then was renamed and moved under Campaign on 2026-07-01 (PR #259) — it’s a real, newly-launched agent, not a relabeled existing one.

2. The chat engine (ai-api, live)

When a user types into Pulson, Action Chat answers — a LangGraph state machine, rebuilt each turn: router → one specialist sub-agent → composer.

Agent	Role	Reads/writes	Model
Router	Classifies the message (query / insight / action / task) and resolves context	Read-only	gpt-4.1-mini
Query sub-agent	Answers about your own performance/sales/budget from Snowflake; draws charts	Read-only	gpt-5.5
Insight sub-agent	External/market lookups — competitors, keywords, ASIN detail (web search)	Read-only	gpt-5.5
Action sub-agent	The only agent that can change an Amazon account — bids/budgets/keywords/targets, custom reports, AMC, optimize-cycle, diagnosis	Write (gated)	gpt-5.5 / gpt-5
Task sub-agent	Manages the internal inbox & tasks	Internal writes only	gpt-5-mini
Composer	Writes the final reply (“Your name is Pulson”)	Read-only	gpt-5.5
Memory Agent	Background — observes each turn, builds durable brand memory (16-card classifier)	Internal writes only	gpt-5-nano

Two adjacent chat surfaces: Pulson / “Growth Twin” (the live brand-facing chat, /pulsy/chats) and PSM (the original engine, legacy/frozen — see the timeline).

3. Report & diagnostic engines (ai-api)

Agent	What it does	Reads/writes
Dashboard Report Agent	The real report engine — a 3-phase pipeline (fetch data → plan directives → render KPI bands / cards / charts / tables). Powers the Reporting generators.	Read-only (writes report rows)
Reporter Agent	Regenerates a single report section on request	Writes report rows
Performance Diagnose	Finds declining SP/SB/SD campaigns, root-causes them, recommends 1–5 actions	Read-only — recommends, never applies
News Intelligence	Brand/market/competitor news briefings via Exa.ai (not an LLM chat agent)	Read-only
Search-term segmentation	Batch-classifies Amazon search terms into segments + brand recognition	Read-only · Gemini 2.5 Flash-Lite (the one non-OpenAI model in ai-api)

4. Autonomous back-office agents (pulsead-agents, 18)

These run on schedules or orchestration in the AWS Bedrock/AgentCore layer. They do the heavy lifting; the in-app agents mostly display their output. Every proposer writes to an approval queue; only an executor acts, and only after approval (and the KISS-only live gate).

Campaign Health — daily monitor → diagnose → fix loop:

• monitoring — daily anomaly detection (ROAS drops, cost surges, Buy Box loss). Read-only. ~07:00 KST Mon–Fri.
• diagnoser — root-causes anomalies, proposes structural actions (pause, audit). Proposer.
• rtb_analyst — RTB rule-group analysis, proposes bid/budget tuning. Proposer.
• executor — applies approved actions (bid/budget/pause). Write, manual-only.

Optimize Cycle — automated budget rebalancing (the engine behind Budget Automation), 1-min schedule poller, two human gates:

• input_checker (P0) → monitor (P2) → rebalancer (P3, proposer) → approval → optimizer (P4, proposer) → approval → executor (P6, write) → verifier (P7, write).

Ads Scheduling — natural-language scheduled changes:

• ads_scheduler (NL → scheduled task) → ads_executor (runs due tasks every minute; write, gated).

AMC — the engine behind AMC Builder:

• router → advisor (answers AMC questions) / writer (generates & saves AMC SQL; does not execute).

Proactive Keyword — alert-driven proposers, now surfaced in-app as Keyword Optimizer:

• keyword_harvester (proposes profitable exact-match keywords) and waste_keyword_pauser (proposes pausing zero-click spend). Both propose → approval card → gated mutation.

Support — reminder-only, added 2026-08-06:

• support_reminder — flags unanswered support items past a threshold and drafts a Hermes reminder. Read + draft only; it does not send or resolve tickets itself.

The Weekly Report LLM pipeline is gone — Pulson Weekly Report still works

Through 2026-06-25, Pulson Weekly Report was powered by an autonomous 4-agent pipeline here (data_preparer ∥ context_builder → report_writer → approval → publisher). That pipeline was deleted (plan 091 Phase 1 — “legacy Aurora weekly report system removal”); it was unrelated to the still-live Snowflake-backed weekly report system (plans 089/090). Today the in-app agent reads published content through ai-api’s weekly_report/weekly-reports API — a plain read/serve endpoint with no agent call in it. Open question: is the report content itself still LLM-assisted at authoring time (via the pulsead-agents ops admin panel), or fully human-curated now? Not resolved from code — flagged in _internal/needs-johnny.md.

5. Operator tooling (separate)

AOP / aop-hermes is a separate operator-facing agent CLI for PulseAd staff — not part of the Pulson product, and not behind the propose→approve gates (its ~45 Amazon Ads write actions are guarded only by per-tool dry-run). See the name map and Capabilities. It’s listed here for completeness; it isn’t one of the in-app agents.

How the layers connect

The in-app agent you click is usually a window onto a backend engine:

In-app agent	Powered by
Budget Automation	Optimize Cycle (6-agent pipeline)
Campaign Optimizer	Action Chat’s Action sub-agent → ads_* mutation tools
Keyword Optimizer	Proactive Keyword back-office agents (keyword_harvester + waste_keyword_pauser)
AMC Builder	AMC agents (router/advisor/writer)
Weekly / Monthly / Daily Report	Dashboard Report Agent
Overview Dashboard / Event Monitoring	Dynamic Dashboard engine (ai-api, shipped 2026-06-19)
Pulson Weekly Report	ai-api weekly-report API, serving ops-curated content (the old back-office pipeline was retired 2026-06-25)
News & Market Intelligence	News Intelligence service (Exa.ai)

Read the per-family pages for the full capability of each in-app agent.