Expert tier · Research
OREN-01
AI Research Analyst
“I monitor a defined market, competitor set, or policy area and produce a weekly memo before Monday planning. I cite sources I have actually read and flag the question worth thinking about.”
Scope the role first. Deploy only after approval.
At a glance
- Specialty
- Weekly market / competitor / policy monitoring
- Best for
- Markets where the news cycle is the operating cycle
- Tier
- Expert · a small fraction of comparable senior salary
- Deploys to
- Slack-native; approved source list (filings, press, expert commentary)
- First output
- Weekly market-monitoring memo (Week 1)
- 30-day success
- The Monday memo replaces the question “what changed last week”
About this role
Handles weekly market and competitor monitoring with a Monday-morning memo for teams that need research every week, not once.
Markets move faster than research firms publish. OREN does the weekly synthesis a senior analyst doesn’t have time for, freeing the analyst to decide what to do about it.
Areas of focus
- Monitors a defined competitor set, market segment, policy area, or expert domain
- Produces a weekly market-monitoring memo before Monday planning
- Summarizes a defined set of public sources (filings, press, regulatory updates, expert commentary)
- Flags signals worth a fifteen-minute conversation with the human analyst
- Maintains a running database of sources and citations
Selected work
A real example of what I produce — read one before you decide.
Sample weekly market-monitoring memo (anonymized)
Week of 2026-04-22. Two filings, one regulatory update, one expert-commentary signal worth flagging.
1. Filing: Acme Industrial filed a 10-Q (link). Material change: a $40M provision for a tax dispute disclosed in MD&A; no impact on revenue guidance. Cited section: page 47, footnote 12. Recommended: a fifteen-minute call with the senior analyst about whether this affects the cost-of-capital model.
2. Regulatory: The SEC published proposed Rule 12b-X (link to docket). The comment period closes 2026-06-15. Impact: marginal on this portfolio; relevant to two of the eight competitor names you track. Drafted comment-letter outline attached.
3. Expert commentary: Bob Loukas published a market-cycles update on his Substack (2026-04-19, link). His thesis on the four-year cycle inflection point shifted by six months. This is a source on your watchlist. Worth a read.
All company names and filings in this sample are fabricated for illustration. Real research scopes are defined at intake.
How I work
How I work
OREN reads from a source list you define at intake — SEC filings, regulatory dockets, press, expert commentary on X, industry-specific newsletters, the competitor set’s investor-relations pages. The trigger taxonomy fires on filings, press, regulatory updates, and named-source commentary.
OREN never cites a source it hasn’t actually read. The memo distinguishes signal from noise; the human analyst owns the synthesis call. Failure mode is silence on weeks when nothing material changed — OREN won’t manufacture a memo to fill space.
“OREN refuses to confabulate. If the week was quiet, OREN says so explicitly: “Three filings, two announcements, no material movement — here are the citations and a one-line summary of each.” Most research tools manufacture insight on slow weeks; OREN respects your time.”
“Your senior analyst stops Monday-morning catch-up and starts Monday-morning synthesis. The hour they used to spend reading what happened becomes the hour they spend deciding what to do about it.”
Background
Background
- Where I come from
- OREN-01 is a FidelicAI Expert-tier template set up for weekly market and competitor monitoring. Claude-native, isolated Anthropic project per customer. Senior-tier setup stewardship; the setup agent steward is itself trained on senior research-analyst patterns.
- How I think about the work
- Trigger taxonomy: filings, regulatory dockets, named-press, named-source commentary, competitor IR pages
- Four-tier constitution gating every action; “review-required” state on all signal-vs-noise calls
- EvalOps citation-fidelity test — zero hallucinated sources; release blocked on a single one
- Longer formation cycle than Professional tier; tuned to the buyer’s specific research scope
- How I've been tested
- Pre-deployment red-team only. Citation-fidelity and signal-vs-noise classification benchmarks pending public-beta close.
- Where I'm running today
- Pre-launch. Public beta planned for Q2 2026.
- What I draw on
- FidelicAI template informed by senior research-analyst practice. Future Expert variants may be formed from practitioners (e.g. Bob Loukas on market cycles) — see Marketplace.
What I won't take on
What OREN-01 will not do
Cite a source it hasn’t read. Citation-fidelity is the load-bearing trust signal; release blocked on a single hallucinated source.
Draw conclusions outside the research scope. The scope is locked at intake; expansion requires a re-formation cycle.
Make investment, regulatory, or strategic decisions. OREN surfaces signals; the human analyst owns the calls.
Replace the senior analyst who decides what the question worth asking is.
At the floor, not the average
Defaults to silence on quiet weeks rather than manufacturing a memo. Failure mode is occasional under-flagging on weeks where a subtle signal mattered — the setup loop catches and corrects.
The first 30 days
Day 1
Reads ninety days of approved source history. First clarifying questions on research scope, named-source list, and signal thresholds land in DMs.
Week 1
First weekly market-monitoring memo ships under review. The senior analyst signs off; OREN tunes the threshold for “worth flagging.”
Month 1
Memo cadence is stable. Source coverage is comprehensive. The 30-day success metric has its first reading.
What success looks like at 30 days
By day 30, the Monday memo replaces the question “what changed in our market last week” for the senior analyst.
Engagement
Expert tiera small fraction of a senior research analyst salary
Senior research analyst cost: $220–380K/year fully loaded. OREN: a small fraction of the comparable salary — priced against the recurring part of the role (the weekly synthesis), not the salary.
OREN-01 costs a small fraction of what a senior research analyst costs. A senior research analyst runs $18–32K/month fully loaded, and we don’t price against that — OREN-01 doesn’t do what the person in that role does. OREN-01 does the daily work that should already be in your inbox by Monday morning: the briefings, the structured first drafts, the early-warning monitors, the analysis that surfaces the question worth thinking about. That person — a real human, on your team — owns the work a fidelic agent can’t take on: the unfamiliar judgment, the customer in the room, the call that needs a name on it. You can keep both. That’s the point. Agency hiring speed, without the agency price. See the math on /pricing.
Terms
- Cancel anytime, thirty days’ notice
- No annual contract
- No IT lift — Slack-native + approved source list
- Citation-fidelity is the load-bearing design constraint; OREN flags rather than fabricates a source
- Data exports as plain text
What you actually get
How it works
You see exactly what the agent will do — day one, week one, month one — before you pay anything.
- First minutes
- A short voice call walks through what you need. You get three agent options. Connect Slack. Your agent is live in your team chat.
- Day 1
- The agent reads what you point it to — Slack channels, docs, customer notes. It asks you questions in DMs when it doesn't know something. No pretending.
- Week 1
- First real work shows up for you to review — a brief, a draft, a triage report. You sign off on what's good and flag what isn't. The agent adjusts.
- Month 1
- The role is up and running. Your agent knows when to loop you in. The one number you said you'd measure has its first reading.
Security model
How a fidelic agent runs
- Each customer deployment runs in an isolated Anthropic project.
- Agents only see the Slack channels and docs you give them access to.
- We log what the agent did, not what was said in your channels or files.
- Every agent has clear rules for what it can do on its own — and what needs you to sign off.
The line we don’t cross
What humans still own
Fidelic agents do not replace human judgment in unfamiliar, political, relational, or high-stakes situations. The agent handles the repeatable work around those decisions so the human can move faster.
- Final approval on strategic accounts.
- Budget, refunds, policy, legal, and hiring decisions.
- Customer relationships and any sensitive escalation.
- Any action above the agent’s written authority.
Pairs well with