Deep research on each account in your market.
S1 agents are SalesOne’s deep research agents. Not a database, not a quick AI lookup: they search widely, read the sources, record each buying signal with its source and date, judge fit with a reason for every reject, find who owns the problem and write a point of view. A second pass reviews the work.In October production runs, S1 agents checked 1,051 companies and kept 249; all 802 turned down kept the reason they failed.
Updated October 20, 2026. SalesOne research team.
What does a deep research agent do on one account?
Seven steps, in the order the work happens, with what each one delivered in our production runs. S1 agents do the homework. Your team builds the relationship.
01
Search widely
Press wires, filings, trade press, sponsor news and the sources your segment names, newest events first.
1,000+
data sources cited so far: SEC filings, press releases, company sites, trade press and public records
02
Read the sources
The pages that matter are opened and read in full, from public sources only.
1,051
companies checked against client profiles in October production runs
03
Record each buying signal with its source and date
A buying signal counts only when it has a source link, is about this company, still holds, and is dated inside its window.
375 of 375
buying signals link their source; 98% are dated to the day
04
Judge fit, with a reason for every reject
Every rule in your profile is checked. A company turned down keeps the rule it failed and the evidence.
802 of 802
companies turned down keep their reason: about three in four of those checked
05
Find who owns the problem
Current people only, from leadership pages, filings and press releases. Anyone who has left is caught and held back.
4.2
people mapped per kept account, on average; 95% with a dated source
06
Write a point of view
What changed, the problem it creates, who owns it and why now, in two sentences tied to the dated facts.
1
point of view per account, written before anyone reaches out
07
A second pass reviews the work
Before delivery, a review pass re-checks every buying signal against its source and looks for fresher news.
On
by default, on every account delivered
Then
The next run starts from this one
Companies already covered, every reject and its reason, and your ratings go into the next research brief.
From SalesOne’s production research runs, October 2026: 249 accounts kept and 802 turned down. How we measure S1 research.
One company, researched three ways
The same sample company through a contact database, a quick AI lookup and S1 deep research. Only one tells you why now, who owns it and where each finding came from.
A sample company, Halvorsen Castings, researched three ways. A contact database returns a record at once: industry, size, revenue, location, a contact who is no longer the COO and an intent topic, with no source or date for any field. A quick AI lookup reads three pages and writes a short general summary with one cited link and no dates. S1 deep research reads the sources, records each buying signal with its source and date, turns down a neighboring company with the rule it failed, finds four people who own the problem, catches that the former COO has left, writes a point of view, and a second pass corrects one buying signal's date.
How do databases, AI lookups and deep research compare?
Twelve angles, compared by kind of tool rather than by product.
| Angle | Contact database | Quick AI lookup | General deep research | Persistent account agents | S1 deep research agents |
|---|---|---|---|---|---|
| Good at | Contact details at scale, fast and cheap. | One well-defined field across thousands of rows, quickly. | One long, cited report on one hard question. | Watching the accounts you give it and noting what changes. | The step before: which companies in a market belong on the list, each with a dated reason, and a verdict for every one turned down. |
| Where candidate companies come from | Filters over records it already holds: industry, size, location, technology. | The list you upload or pull from a database. It researches the rows it is given. | Whatever the one question names. Not built to list every company in a market. | The accounts you give it, usually a named list or your CRM. | Starts from dated events in filings, press wires and trade press, and builds the list against your profile. |
| Depth on each account | A fixed record: company facts, technology and contacts. | One question per column. More depth means more columns, each billed. | Many pages read for one long report on one question. | Research that builds up on each tracked account over time. | Each account researched in depth into the same checked fields, from 1,000+ data sources. |
| Checking each fact | Record-level checks, such as email validation. No source shown for each fact. | Varies. The best tools check each criterion with a cited link; most return free text. | Cited prose. Independent audits find that a share of citations do not support the claim. | Varies by maker. Some keep a reasoning trace for each decision. | Each buying signal keeps its source link, and a second pass re-checks every one before delivery. |
| Freshness and dates | Refreshed on the provider’s cycle. No date on each fact. | As fresh as the page read that day. The source date is rarely shown. | Current when it runs. Nothing is re-checked unless you ask again. | Kept current on the accounts it tracks. Dates on each fact vary by maker. | Every buying signal carries the date it happened; 98% are dated to the day. |
| Sensing what changed | Company-level topic intent and news alerts. Broad and low cost. | Only when you run the column again. Some newer agents track changes per account. | None. Each report is one run. | Watches the accounts it is given between your requests. | S1 starts every search from dated events and keeps only triggers inside their window; accounts whose window is open are flagged, and a fresh check runs before outreach. |
| Qualification, with reasons | Filters and scores, without a written reason. | Possible if you write the rubric yourself. | An opinion in prose, not a verdict against your profile. | Works accounts already chosen, so turning companies down is rarely its job. | Judged against every rule in your profile. Every reject keeps the rule it failed and the evidence. |
| Buying committee | Contacts by title and department across very large record counts. | Usually one person per prompt, such as the head of operations. | At least one maker limits compiling details about individual people. | Some identify stakeholders on each tracked account. | About 4 current people per account who own the problem; 95% carry a dated public source. |
| Point of view | None. Data only. | A personalized line per row. | A long report, not a reason to reach out. | Account summaries and suggested next steps. | A short point of view per account, tied to its dated facts. |
| Human approval | Not applicable: it supplies data. | Depends on the tool. Some send messages on their own. | Not applicable: it writes a report. | Depends on the tool. Some act on deals on their own. | A person approves every message before it goes. |
| Feedback into the next run | None for your account. | You edit the prompt. | None across runs. | Builds on what it learned about each account. | Your fit ratings, and the reasons behind them, go into the next research brief. |
| Memory of what was covered | The same records for every customer. | Rows in a table. Most runs start fresh. | None. Each report stands alone. | Memory for each account it tracks. | Remembers every company checked for you and never researches one twice. |
| Cost model and output | Seats and credits per contact. Output: rows. | Credits per row and per column. Output: cells. | Per report, or a plan with a monthly quota. Output: prose. | Platform plans; cost per account is rarely published. Output: updated account records. | Priced on qualified accounts; companies turned down are explained and not charged. Output: researched accounts. |
| Not built for | Saying which accounts fit and why now, with a source and date for each fact. | Qualifying against your profile, or keeping a reason for each company left out, unless someone builds it. | Every company in a market, in the same checked fields. | Deciding which companies in a market belong on the list. | A contact list with no research behind it. |
Categories, not named products, from the makers’ own documentation, October 2026. The citation audits are DeepResearch Bench (2025), DeepTRACE (2025) and the Columbia Journalism Review’s Tow Center study of AI search (2025). For named tools, see the best AI tools to research accounts.
How well does S1 research hold up?
Every figure comes from SalesOne’s own production runs or a published outside benchmark, and every one links its method. The figures for each step are above.
What the production runs delivered
Every decision has a reason and a source. Before delivery, a review pass re-checks every buying signal against its source. Nothing is researched twice for a client.
249 of 1,051
companies checked were kept. About three in four were turned down, each with its reason.
802 of 802
companies turned down kept the reason they failed, so a familiar name that is missing can be explained.
375 of 375
buying signals link their source, and 98% are dated to the day.
1,000+
data sources cited so far: SEC filings, press releases, company sites, trade press and public records.
SalesOne production research runs, October 2026. How we measure S1 research.
Why general deep research is not built for this
General deep research tools are excellent at one long report on one question. Researching every company in a market into the same checked fields is a different job, and an independent benchmark measures exactly that.
5.1%
of tasks fully completed by the best general agent on WideSearch, a benchmark of collecting every entity in a set into a table (the best agent tested; dedicated deep research products were left out because they returned reports instead of tables).
2.4%
average success for the best agent on DeepWideSearch, when finding each entry also took multi-step reasoning.
Sources: WideSearch, arXiv 2508.07999, August 2025 (opens in a new tab); DeepWideSearch, arXiv 2510.20168, October 2025 (opens in a new tab). Both measure general AI agents; neither tested S1.
Want to see it on your own market? Book a call and we will show you the accounts S1 agents keep, the ones they turn down, and why.
Which AI models do S1 agents use?
S1 agents run on large AI models, tested by SalesOne before they research for clients, under SalesOne’s own rules. What matters to your team is what those rules guarantee, whichever model runs.
What your team gets
- Nothing researched twice: every run reaches accounts your team has not seen.
- Every decision with a reason and a source you can open.
- Every buying signal re-checked against its source before delivery.
- A person approves every message, and every approval is recorded with who gave it.
Rules no agent can skip
- Before research starts, every company is checked against what was already researched for you and your exclusion lists, and existing SalesOne clients are never researched.
- No account accepted or turned down without a written reason.
- A person counts as ready only with a dated source from the last 12 months.
- Public sources only.
How does S1 know what changed?
S1 starts from what changed: every account begins with a dated event inside its time window, and accounts whose window is open are flagged.
Each buying signal has a window, set in your ideal customer profile for each target group: by default a new executive counts for 180 days, and the first 90 come first. SalesOne puts accounts with an open window first and shows the date to reach out by.
Every run starts from the newest dated events, and before outreach a fresh check looks for dated facts from the last 12 months.
What does each run build on?
The companies already covered, every reject and its reason, and your team’s fit ratings, which go into the next research brief.
Nothing researched twice
Companies already covered for you, your exclusion lists and existing clients are skipped, so every run reaches accounts your team has not seen.
Reject reasons that suggest a change
SalesOne counts the reasons companies were turned down and suggests a change to your profile. A person confirms it before the next run uses it.
Your team’s fit ratings
The ratings your team gives accounts, with their reasons, go into the next research brief, so each run builds on the last.
Replies and call outcomes are captured in SalesOne, on each account’s history; they do not change the research.
Questions buyers ask
What are S1 agents?
S1 agents are SalesOne’s deep research agents. They search your market for companies with a dated reason to change and work each one the way a senior researcher would: search widely, read the sources, record each buying signal with its source and date, judge fit against your profile with a reason for every reject, find the people who own the problem and write a point of view. A second pass re-checks every buying signal against its source before delivery, and a person approves every message before it is sent.
Is SalesOne a contact database?
No. SalesOne is not a contact database: it does not sell records to search or export. S1 agents research and qualify each account from dated, sourced public evidence, and contact details are looked up only for the people your team picks.
How is this different from an AI research column in a spreadsheet tool?
An AI column asks one question per row, which is quick and cheap. S1 agents work the whole account: the sources read, every rule in your profile checked, the buying committee found and a point of view written, then a second pass re-checks every buying signal. The output is a qualified account, not a cell.
How do S1 agents check facts?
A buying signal counts only when it has a source link, is dated to the day (to the month when the source gives no day), is about this company and not a parent or a customer, still holds, and falls inside its window. Before delivery, a review pass re-checks every buying signal against its source and looks for fresher news.
How fresh is the research?
Every buying signal carries the date it happened, and 98% are dated to the day. Every run starts from the newest dated events, and before outreach a fresh check looks for dated facts from the last 12 months.
What does deep research cost?
SalesOne is priced on qualified accounts, not database rows or credits. Each account is delivered with its deep research. Companies S1 agents turn down are researched too, explained and never charged. Plans are quoted on a call, based on your market and the number of accounts you need.
Related reading
- Account research
Product
- Buying committee mapping
Product
- What each run builds on
Product
- How pricing works
Pricing
- Best AI tools to research accounts before outreach
Comparison
- ZoomInfo alternatives: cheaper data or deeper research
Comparison
- How we measure S1 research
Method
See your own market, researched.
Bring your offer and one customer you would like more of. We will research a sample of your market and show you the accounts S1 agents accept, the ones they turn down, and why.