InsightTerminal X · market & regulatory data agents
For portfolio managers, brokers and research desks. Agents collect SEBI portfolio-manager filings, PMS performance, ETF liquidity and index changes the moment they’re published — cleaned, versioned and exported the same way every month.
WhySound familiar?
From research heads at portfolio managers, brokers and wealth desks. Composite quotes from discovery calls — the problems are real; the names are left out.
“Two analysts lose the first week of every month to copy-paste.”
Every manager, eight sub-reports each, one page at a time — then cleaning the merged cells before anyone can analyse a thing.
Head of research40+ analyst hours a month
“We only track the managers we have time for.”
The full universe is too big to collect by hand, so the competitive view is the same twenty-five names every month.
Product & distribution headMost of the market unseen
“The merge broke and nobody noticed for a month.”
A portal renamed a column. The lookup returned blanks, the sheet still looked fine, and the model ran on it.
Quant analystDecisions on silently bad data
HowWhat changes with Terminal X
Product screens with illustrative, anonymised data. In your walkthrough we run the agents on the sources your team uses.
01Copy-paste week
The first week of the month back
02Partial coverage
Every strategy, every month
03Silent breaks
Trust the number in the export
FieldTerminal X in the field
The workplace it runs in, the person who uses it on a phone, the team at the desk and the detail it reads.
Photographs are illustrative — real customer sites are not shown.
01Open Terminal X
Click through it. A SEBI PMR run works through every manager in parallel, PMS returns line up against the benchmark you choose, ETFs get flagged for premiums, index changes appear, and the Excel reconciles its own scheme counts.
Illustrative and anonymised — managers, strategies, ETFs and constituents are labelled by code, not by name. Figures are not market data.
02Four agents
The sources are public. The work of collecting them is not small. Each agent runs on a schedule, stores every record with its history, and hands back the same export every time.
Every registered portfolio manager, every month: AUM by service, clients by category, inflows and outflows, turnover, transactions, schemes and complaints.
1M to 3Y returns for every PMS strategy, discretionary and non-discretionary, against Nifty 50 or Nifty 500 — archived month by month.
Price, NAV, premium or discount, traded value and 52-week range for every listed ETF, archived every session.
Listings and constituent files for every strategy index, with added, removed and re-weighted names tracked across runs.
03Source to spreadsheet
The same pipeline runs behind every agent — so a new source is a new agent, not a new project.
Schedule or new-data trigger
Daily, after market close, monthly — or the moment a regulator publishes a new month.
Real browser, parallel windows
The agent works the portal the way an analyst would: filters, dropdowns, pages, downloads.
All rows, all sub-reports
Every manager, every strategy, every ETF — not the twenty an analyst has time for.
Numbers as numbers
“12.4%”, “(3.2)” and “--” become 12.4, −3.2 and blank. Names matched by registration number or ISIN.
Checks before storage
Scheme counts reconciled, duplicates removed, empty filings marked as “no data”, not zero.
Change detection
Each run is compared with the last; what was added, removed or revised is kept.
Source · time · run · version
Every record knows where it came from and when — years of history, queryable.
Excel · API · alerts
The same export every month, a REST endpoint for your models, an alert when something moves.
04Built for research teams
The four agents are the standard layer. Other exchanges, regulators, company filings or your own vendor portals become custom agents in the same terminal, with the same exports, API and audit trail.
Exports match what is on screen, and every record keeps its source and time.
Errors retry, empty filings are marked, layout changes are reported.
Predictable sheets, consistent columns, numbers as numbers.
Managed cloud, your own infrastructure, or both.
FAQQuestions we get about Terminal X
Terminal X is an Autowhat AI product for research heads at portfolio managers, brokers and wealth desks. Short, factual answers for buyers, procurement and the assistants people ask first.
In short. Terminal X is an Autowhat AI product for research heads at portfolio managers, brokers and wealth desks. It is built for research heads at portfolio managers, brokers and wealth desks. It exists to remove the problems those teams describe in almost every first conversation: forty-plus analyst hours a month of copy-paste; a competitive view limited to the same twenty-five names; and models running on silently broken lookups. With Terminal X, teams get every filing collected in one run, with a live count of done, pending and errors, the whole universe ranked the way you ask, stored as numbers, and every run logged: what was collected, how long it took, what changed. It connects to Browser agents, Versioned datasets, Excel / CSV export and Change alerts, is used by Research · product · compliance, and runs on desktop cockpit. Like every Autowhat AI product, Terminal X goes live on one site, lane or process first, usually within weeks, on managed cloud, in your own VPC or on-premises, and shares one operational record with the other products, so the second deployment reuses the data and integrations of the first.
Research heads at portfolio managers, brokers and wealth desks. Agents that collect regulatory filings, portfolio returns, ETF liquidity and index changes across the whole universe — cleaned, versioned and exported — and report every layout change at the source instead of swallowing it.
forty-plus analyst hours a month of copy-paste; a competitive view limited to the same twenty-five names; models running on silently broken lookups.
every filing collected in one run, with a live count of done, pending and errors; the whole universe ranked the way you ask, stored as numbers; every run logged: what was collected, how long it took, what changed.
It connects to Browser agents, Versioned datasets, Excel / CSV export, Change alerts. Users: Research · product · compliance. Channel: Desktop cockpit.
With a 30-minute working session on your own data — an engineer from the relevant sector, not a sales queue. The first wave is scoped in that call; most products go live on one site, lane or process within weeks and then scale.
On managed cloud, in your own VPC (AWS, Azure or GCP) or on-premises, with your keys. SOC 2 Type II and ISO 27001 controls, India data residency when required, and local or open-weight models when policy demands it. The data stays yours.
05Walkthrough
A working session with the engineers who build it: a live SEBI PMR run, your export format, and a plan for the sources only your team uses.
