FO-01Phase 1
Morning Macro Brief
A 6:30 a.m. brief in house style covering overnight markets, central-bank moves, and the day's top movers across our holdings.
Buy-side intelligence layer · Draft for sponsor review
Fifteen agents that think alongside the investment team — never instead of them.
A single, governed AI layer that plugs into Bloomberg, FactSet, Refinitiv, Aladdin, the custodian and the OMS — and turns the recurring drafting, reconciling and triage work into a five-minute review instead of a five-hour build. Every number is cited. Every action waits for a human. Every step is logged for seven years.
15
Narrowly scoped agents
24mo
Three-phase rollout
400–600hrs
Freed per month at maturity
0
Autonomous external actions
The problem
Senior people spend the morning stitching, not thinking.
Every working day, the same recurring outputs are hand-assembled from four or five vendor screens and a handful of internal documents. The data is already there. The judgement is already in the team's head. What's missing is the layer that does the assembly.
Front office
Two days for a first-draft IC memo.
An analyst spends a day and a half pulling fundamentals, peer comps, ESG flags and the last three IC discussions. The actual original thinking takes hours, not days.
Middle office
Compliance breaches noticed late.
Less than half of mandate breaches are surfaced inside an hour. By the time someone reads the alert, contextualises it and routes it, the trade has already cleared.
Back office
Recon breaks closed by hand.
Ops opens twelve breaks every morning, classifies each one, drafts a custodian email, and chases responses. The classification is rules-based; the drafting is templated; nothing is decided.
The fifteen agents
One job, one persona, one human gate.
Every agent does exactly one thing. It reads from systems of record, drafts an output, and stops at a human-approval gate before anything irreversible happens. No agent places trades, files documents, sends letters or modifies records on its own.
BO-01Phase 1
Recon Break Triage
Pulls every open break at 7 a.m., classifies by type, drafts the custodian email, and routes to the right operations owner.
MO-01Phase 1
Risk Morning Brief
One-page risk summary at 7 a.m.: VaR, factor exposures, tracking error, stress-scenario flags — every number cited to the risk engine.
MO-02Phase 1
Attribution Commentary
Drafts Brinson and Karnosky-Singer attribution in plain English. Allocation, selection, currency — broken out and explained.
BO-04Phase 1
Document & Audit Trail Concierge
Natural-language search across IPS, IC minutes, custodian notices, sell-side research, internal memos and emails — with sentence-level citations.
FO-02Phase 2
IC Memo Drafter + Devil's Advocate
First-pass IC memo from the research packet, plus a structured counter-argument that cites specific contradictory sources.
MO-03Phase 2
Compliance Breach Triage
Reads Charles River / AIM alerts the moment they fire, classifies severity, drafts the narrative, escalates to the compliance officer.
BO-02Phase 2
Corporate Action Interpreter
Reads SWIFT MT564 and issuer notices, recommends an election with rationale, flags portfolio impact. Human approves before the custodian is told.
BO-03Phase 2
Cash Ladder + FX Funding
Multi-currency cash ladder twice daily. Identifies funding gaps, suggests forward rolls, surfaces expiry dates before they bite.
FO-04Phase 2
Earnings Call Synthesiser
Triggered when an earnings call ends. Fifteen-minute summary with deltas vs the last four quarters, cited to transcript timestamps.
MO-05Phase 2
Liquidity Coverage Monitor
Days-to-liquidate per holding under stress; coverage versus the liability profile; alerts when a position outgrows its venue.
MO-04Phase 3
Mandate-to-Rule Agent
Translates IPS / IMA clauses into structured CRD or AIM rule drafts. Two-person sign-off mandatory. Highest-stakes agent in the platform.
FO-05Phase 3
Manager Selection Analyst
Peer set construction, DDQ synthesis, Form ADV ingestion, red-flag detection. Conditional on holding external funds.
FO-06Phase 3
Client Letter Drafter
Quarterly letter first draft in house voice. PM, IR and Compliance sign off before anything leaves the firm. Conditional on external clients.
FO-03Phase 3
Pre-IC Research Packet
The full pre-IC packet — peer set, fundamentals, ESG, prior diligence, technicals. Last on purpose: it consumes every other agent.
A day in the life
Five worked examples — actual outputs the team would see.
Every example below is what the user actually receives — the brief in Slack, the recon table at 7 a.m., the IC memo with its devil's advocate, the breach card on the compliance desk, the Q&A from the document concierge. None of it is final without a human approving it.
06 : 30
Local · Mon
The Morning Macro Brief lands in Slack FO-01
Before the PM has finished their coffee, the brief is in #front-office. It's not a digest of headlines — it's the firm's own portfolio against an overnight market backdrop, written in the firm's voice, with every figure traceable to the system it came from.
A
Morning Brief
Agent · FO-01
06:30
Overnight setup. Asia closed mixed; Nikkei +0.4%, HSI -1.2% on property weakness. Bunds rallied 6bp after softer German PPI. DXY +0.3%, USDJPY through 158 — currency overlay flagged for review.
Top movers across our holdings
- ASML NA · semis cyclical+3.8% FactSet · 06:24 UTC
- Aramco · upstream KSA+1.2% Bloomberg · 06:18
- SolarEdge · clean energy-7.1% FactSet · pre-mkt
- JD.com · China consumer-2.4% HKEX close
Calendar today. ECB minutes 12:30 UTC. US CPI tomorrow — Risk Brief flagged elevated rate sensitivity in the EU credit sleeve.
07 : 00
Local · Tue
Twelve recon breaks, triaged before anyone opens email BO-01
By the time Operations sits down, every open break has been pulled from Duco, classified, written up, and routed. The ops manager isn't deciding what to do — they're confirming the triage and pressing send on the custodian email.
| Break | Class | Severity | Drafted action | Owner |
|---|---|---|---|---|
| BRK-44218 | Position · TSLA | Material | Custodian email + chase trade ticket TR-9812 | L. Park |
| BRK-44219 | Cash · USD | Review | FX settlement timing — propose T+1 reclass | F. Halim |
| BRK-44220 | Price · ASML NA | Auto | Stale BVAL; refreshed at 06:58 — clear | Auto-cleared |
| BRK-44221 | Corp action · BHP | Review | Stock split 1:3 not yet booked at custodian | L. Park |
| BRK-44222 | Position · 7203 JP | Low | 1-share rounding; flagged for monthly clean-up | Queue |
| BRK-44223 | Cash · EUR | Material | Funding gap €4.2m — see Cash Ladder agent | Treasury |
Showing 6 of 12 breaks. 10 auto-classified · 2 escalated for human triage.
Mean draft time per break: 38s
All actions require operator approval before send.
11 : 00
Local · Wed
An IC memo, drafted in 40 minutes — with its own counter-argument FO-02
Yesterday this memo would have taken two days to assemble and a day to argue with. Today the analyst kicks the agent off after the morning meeting. The memo and a structured devil's-advocate argument are ready before lunch. The analyst spends the afternoon refining the thesis, not pulling fundamentals.
Novo Nordisk — Recommend overweight, +120 bps active
Thesis. GLP-1 demand visibility extends through 2028 on capacity additions at Kalundborg and Catalent fill-finish[1]. Pricing pressure in the US is real but smaller than the Street fears: rebate disclosures suggest a 6–8% net realised price decline against the consensus 12%[2].
Position size. 1.4% active vs benchmark 0.6%. Liquidity check: 8 days to fully liquidate at 25% ADV[3]. Currency overlay: DKK exposure already inside policy band.
Catalysts. Q4 capacity guidance update (Nov), CagriSema PIII top-line (early 2027), oral semaglutide CV outcomes data (mid-2027).
Devil's Advocate · structured counter
Three independent sources contradict the rebate-disclosure thesis. Express Scripts' 2026 formulary memo[4] guides to 14% net price erosion; this is the same number CVS cited on its 2Q call[5]. If those are correct, our base case overstates 2027 EBITDA by ~9%. The position remains supportable but the size should be 80–100 bps, not 120.
[1] Novo Q3 transcript p.14 · [2] BBG NRX rebate dataset · [3] Internal liquidity engine · [4] Express Scripts memo Aug 2026 · [5] CVS 2Q call transcript p.22
14 : 14
Local · Thu
A breach surfaced and classified within minutes MO-03
Charles River fires an alert at 14:14. Eleven minutes later the compliance officer has the full picture: which mandate clause, which positions, what the rule actually says, severity, and a draft narrative. The officer's job is to confirm and act — not to assemble.
Single-issuer concentration limit exceeded — Microsoft holdings now 5.4% vs 5.0% mandate cap.
The breach is driven by mark-to-market drift, not a new trade. Two adjacent funds are within tolerance. The relevant clause is IPS §4.3.bIPS-2024 v3 · §4.3.b — concentration measured at month-end on a look-through basis. The look-through is not yet stale; the breach is real.
Recommended action: trim 0.5% over the next 3 trading days using the standard 25% ADV ramp. No client notification required under §4.3.b.iii.
16 : 30
Local · Thu
"What did we agree about EM exposure last September?" BO-04
A simple question that used to mean digging through SharePoint, email and IC minutes for an hour. Now it's a sentence. The agent retrieves from every indexed corpus — IPS, IC minutes, custodian notices, internal memos — and answers with sentence-level citations. No invented quotes, no paraphrased numbers, no guesses.
What did we agree about EM exposure in the September IC?
The 14 September IC ratified a tactical reduction in EM equity from 14% to 10% over two months, with the residual 4% redirected to short-duration EM hard-currency credit. The decision cited weakening EM real-rate differentials and an explicit concern about USD strength into Q4. The IC also agreed to revisit the cap at the December meeting.
[1] IC Minutes 14 Sep 2026 · §3 (Asset Allocation) · "tactical reduction approved unanimously"
[2] IC Minutes 14 Sep 2026 · §4.2 · "redirect to short-duration EM credit"
[3] Pre-IC research packet 12 Sep · macro section p.6 · real-rate chart
[4] Quarterly review draft Sep 2026 · §EM allocation · "December review checkpoint"
How it works
A read layer, a reasoning layer, a human-approval layer, and a permanent log.
The platform is small in concept and disciplined in design. It reads from systems of record, retrieves from the firm's own document corpus, asks an LLM to reason within tight guardrails, asks a human to approve anything irreversible, and writes everything to an immutable log.
01 · DATA
Read, never write
Bloomberg, FactSet, LSEG, Aladdin, custodian, prime broker, OMS, IPS / IMA documents, IC minutes, emails. Read-only access; every datapoint tagged at ingest.
02 · GROUND
Retrieve before reasoning
For every claim the agent might make, it retrieves the underlying source first — keyword and semantic search across every indexed corpus, with sentence-level citation enforced.
03 · REASON
Numbers from systems, words from the model
The LLM is allowed to write prose, draw conclusions, propose actions. It is not allowed to invent figures. Every quantitative claim must trace to a source.
04 · APPROVE
Human gate, every time
Nothing irreversible — a custodian email, a filed document, a client letter, a rule change — leaves the platform without a human approving it in Slack or the web app.
05 · LOG
Seven-year immutable trail
Every prompt, every retrieval, every tool call, every approval, every output is written to a hash-chained, write-once log retained for seven years. No exceptions.
The timeline
Two years, three phases, fifteen agents — shipped in the right order.
Year one builds trust with five low-risk, high-payoff agents. Year two ships the harder middle and back-office work and starts the formal model-risk programme. Year three completes the regulator-sensitive agents and finishes validation.
Phase 1 · Foundation
Build trust.
Months 1 — 6
- Five agents in production: Morning Macro Brief · Recon Break Triage · Risk Morning Brief · Attribution Commentary · Document Concierge.
- Foundations live: identity, audit log, prompt registry, eval harness, human-in-the-loop UI.
- Two vendor connectors: Bloomberg + one custodian. Two document corpora: SEC filings + internal IC memos.
Phase 2 · Expansion
Earn the harder agents.
Months 7 — 14
- Six agents added: IC Memo Drafter + Devil's Advocate · Compliance Breach Triage · Corporate Action Interpreter · Cash Ladder + FX · Earnings Call Synthesiser · Liquidity Coverage.
- Vendor expansion: LSEG MCP server, Aladdin APIs, prime broker, full email and Slack archive.
- SR 11-7-style model risk programme started; first three agents formally validated by an independent reviewer.
Phase 3 · Maturity
Harden for scrutiny.
Months 15 — 24
- Four final agents: Mandate-to-Rule · Manager Selection (conditional) · Client Letter (conditional) · Pre-IC Research Packet — last because it consumes every other agent.
- All 15 agents formally validated under SR 11-7. Annual recertification cycle running. SOC 2 Type 2 received.
- Quarterly fitness reviews live. At least one agent retired or materially reworked based on telemetry — proof the kill criteria are real.
Trust & safety
The four hard rules — baked in, not bolted on.
These are not policies on a slide. Each one is enforced at the platform layer: a misconfigured agent cannot bypass them. Failures fail closed — the agent stops, an incident is logged, and the action does not happen.
Every number is cited
No quantitative claim leaves an agent without a citation back to a system of record. The model can write prose. It cannot invent figures. A second model — the verifier — independently checks every quantitative claim before publication. Citation coverage target: > 99%.
Every action waits for a human
Agents are read-only by default. Anything irreversible — sending a custodian email, filing a document, drafting a client letter, modifying a compliance rule — pauses at a human-approval gate. The gate is enforced at the workflow engine, not the UI.
Every step is logged
Every prompt, every retrieved document, every tool call, every approval, every output is written to an immutable, hash-chained, write-once log retained for seven years. If the log is unreachable, the agent stops — no action, no exception.
MNPI is segregated at ingestion
Every datapoint is tagged at the moment it enters the platform — PUBLIC, LICENSED, RESTRICTED, MNPI. Agents declare which tags they may consume. The platform hard-fails any attempt to route restricted material into a channel that doesn't permit it.
Regulator posture
Every agent is treated as a model under SR 11-7. Each one has a model card, a declared eval suite, an independent validator, and an annual recertification date. The platform's audit posture is built to clear SOC 1 and SOC 2 Type 2 attestation by Month 24, and to produce, on demand, a complete trace of any output ever generated — what data went in, which model produced it, who approved it, when, and why.
The numbers we'll watch
A simple dashboard. Honest indicators.
The programme is judged on five things. Hours freed. Quality at-or-above the human first draft. Zero control failures. Clean model-risk posture. And — most importantly — at least one agent retired or reworked based on telemetry. A programme that never kills anything isn't reviewing honestly.
Programme dashboard · sample at month 24
Live
Hours freed / month
487hrs
↗ +18% vs M18
Recurring outputs drafted by agents
85%
↗ on Phase 3 target
IC memo time-to-first-draft
0.4days
↘ from 2.5 days at start
Breaches surfaced in < 1 hr
96%
↗ above target
Cost per agent-output (vs M6)
−54%
↘ ahead of plan
Hallucination rate (verified)
0.21%
↘ within tolerance
Agents validated (SR 11-7)
15 / 15
✓ complete
Agents retired or reworked
2
⌥ honest pruning
The dashboard above is a representative sample. Actual figures will be reported monthly to the steering committee from Month 1; the targets are documented in SUCCESS_CRITERIA.md.
What happens next
Six decisions stand between this document and Month 1.
Phase 1 cannot kick off until the foundational scope decisions are made. None of them are theoretical — each one shapes infrastructure, vendor selection, or compliance posture. The full list of fourteen open questions is in the PRD; below are the six most consequential.
i.
Cloud or on-premises deployment?
Drives the entire infrastructure plan and dictates whether Year 3's on-premises LLM line item is needed. Driven by data-residency obligations under PDPL, GDPR, and any specific regulator guidance.
Decision · Month 0
ii.
Aladdin or Bloomberg AIM as anchor?
The choice of anchor OMS / risk system determines which adapter is built first and which golden-source conflict-resolution rules apply. Consequence flows through Phase 1 and Phase 2.
Decision · Month 1
iii.
Recon engine selection: Duco, SmartStream, AutoRek?
Recon Break Triage is a Phase 1 agent. Its triage taxonomy depends on the recon engine's break schema. The decision must precede agent development.
Decision · Month 1
iv.
Bloomberg licence scope for LLM use
Does the firm's Bloomberg licence permit Bloomberg-sourced data to be included in prompts sent to third-party LLM endpoints? If not, the Bloomberg path stays inside Bloomberg's own AI tools (ASKB) or moves on-premises.
Decision · Month 1 · Legal owns
v.
Do we hold external funds? External clients?
Two Phase 3 agents are conditional on these answers — Manager Selection (FoF holdings) and Client Letter Drafter (external LPs). If neither applies, Phase 3 effort is redirected to platform hardening.
Decision · Month 9
vi.
LLM enterprise contract tier
Direct Anthropic, AWS Bedrock, or Azure AI Foundry? The choice affects data-residency guarantees, BAA / DPA terms, rate limits and prompt-caching availability. Procurement decision driven by Compliance.
Decision · Month 2