features

The final dataset: one capability statement per row, each with a verbatim excerpt of the archived documentation it rests on. This is release/features.csv.

Data license: Not yet licensed — internal review only · Data source: Ahmed ElBatanony, Innopolis University

form
user-action = 'The system lets …'; automation = 'The system automatically …'.
found_by
Which blind run's wording was kept (the other run may also have found it), or verifier/adjudicator for added capabilities.
verification
confirmed by the verifier; corrected (reworded); or added (missed by both runs).
pipeline_id
Link to the full pipeline record of this statement.
source_sha256
sha256 of the archived plain text the excerpt was checked against.
audited
1 if the row is in the 150-row blind audit sample.
audit_correct
Blind auditor's overall verdict (1 = acceptable as is).

53 rows where app_id = "F1-005" and found_by = "extract-a" sorted by feature_id

✎ View and edit SQL

This data as json, CSV (advanced)

Suggested facets: source_url, source_file, source_sha256, found_by_runs, audited

verification 2

form 2

audit_correct 2

found_by 1

  • extract-a · 53 ✖

app_id 1

  • DeskcommCRM · 53 ✖
feature_id ▼ app_id statement form excerpt source_url source_file source_sha256 found_by found_by_runs verification pipeline_id audited audit_correct audit_note
F1-005-S001 DeskcommCRM F1-005 The system automatically answers customer messages on WhatsApp with AI agents automation AI agents that answer, qualify and sell on WhatsApp https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system automatically answers customer messages on WhatsApp with AI agents F1-005-A001 0.0    
F1-005-S002 DeskcommCRM F1-005 The system lets a user receive and answer WhatsApp conversations in an inbox where people and the AI work side by side user-action **Inbox** (WhatsApp conversations, you and the AI side by side) https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets a user receive and answer WhatsApp conversations in an inbox where people and the AI work side by side F1-005-A002 0.0    
F1-005-S003 DeskcommCRM F1-005 The system automatically qualifies leads with AI agents automation AI agents with per-tenant RAG answer customers, qualify leads, move them through the pipeline, trigger automations and know when to hand off to a human https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system automatically qualifies leads with AI agents F1-005-A003 0.0    
F1-005-S004 DeskcommCRM F1-005 The system automatically moves a qualified lead to another pipeline stage and records the reason for each move automation Once qualified, it changes pipeline stage. The tag lands, the owner is set — and every move carries a recorded reason. https://deskcomm.com.br/en 02.txt 1bfa7ae4165a966bc9e1f62b8f5a54e829812cf2a67ce4e76471ad3d2fdc0c59 extract-a both confirmed The system automatically moves a qualified lead to another pipeline stage and records the reason for each move F1-005-A004 0.0    
F1-005-S005 DeskcommCRM F1-005 The system automatically searches a company knowledge base when an AI agent answers a customer automation It searches your company’s knowledge base https://deskcomm.com.br/en 02.txt 1bfa7ae4165a966bc9e1f62b8f5a54e829812cf2a67ce4e76471ad3d2fdc0c59 extract-a both confirmed The system automatically searches a company knowledge base when an AI agent answers a customer F1-005-A005 0.0    
F1-005-S006 DeskcommCRM F1-005 The system automatically runs seven checks on every AI message before sending and records each result, including blocks automation Seven checks before sending https://deskcomm.com.br/en 02.txt 1bfa7ae4165a966bc9e1f62b8f5a54e829812cf2a67ce4e76471ad3d2fdc0c59 extract-a both confirmed The system automatically runs seven checks on every AI message before sending and records each result, including blocks F1-005-A006 0.0    
F1-005-S007 DeskcommCRM F1-005 The system automatically hands a lead to a human with a summary of what happened, what was agreed and the next step automation Not the raw thread: a summary of what happened, what was agreed, which objections came up and what the next step is. https://deskcomm.com.br/en 02.txt 1bfa7ae4165a966bc9e1f62b8f5a54e829812cf2a67ce4e76471ad3d2fdc0c59 extract-a both confirmed The system automatically hands a lead to a human with a summary of what happened, what was agreed and the next step F1-005-A008 0.0    
F1-005-S008 DeskcommCRM F1-005 The system automatically schedules a follow-up when nobody replies automation A follow-up is scheduled. https://deskcomm.com.br/en 02.txt 1bfa7ae4165a966bc9e1f62b8f5a54e829812cf2a67ce4e76471ad3d2fdc0c59 extract-a both confirmed The system automatically schedules a follow-up when nobody replies F1-005-A009 0.0    
F1-005-S009 DeskcommCRM F1-005 The system automatically revives cold conversations with follow-ups using adaptive timing and per-stage triggers automation follow-up that revives a cold conversation (with adaptive timing and per-stage triggers) https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system automatically revives cold conversations with follow-ups using adaptive timing and per-stage triggers F1-005-A010 0.0    
F1-005-S010 DeskcommCRM F1-005 The system lets a user see open requests classified by risk in a Radar based on time without interaction user-action Every open request is classified by time without interaction and by what’s still pending. https://deskcomm.com.br/en 02.txt 1bfa7ae4165a966bc9e1f62b8f5a54e829812cf2a67ce4e76471ad3d2fdc0c59 extract-a both confirmed The system lets a user see open requests classified by risk in a Radar based on time without interaction F1-005-A011 0.0    
F1-005-S011 DeskcommCRM F1-005 The system automatically records every meaningful mutation as an activity on a visible timeline automation Every meaningful mutation becomes an activity on the timeline, visible on screen. https://deskcomm.com.br/en 02.txt 1bfa7ae4165a966bc9e1f62b8f5a54e829812cf2a67ce4e76471ad3d2fdc0c59 extract-a both confirmed The system automatically records every meaningful mutation as an activity on a visible timeline F1-005-A012 0.0    
F1-005-S012 DeskcommCRM F1-005 The system lets a user see a notice center for what needs a human decision user-action a notice center for what needs a human decision https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets a user see a notice center for what needs a human decision F1-005-A013 0.0    
F1-005-S013 DeskcommCRM F1-005 The system lets a user see whether an AI agent is improving and where it fails on an AI Evolution screen user-action the **AI Evolution** screen shows whether the agent is improving, where it fails and what's left to teach https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets a user see whether an AI agent is improving and where it fails on an AI Evolution screen F1-005-A014 0.0    
F1-005-S014 DeskcommCRM F1-005 The system automatically turns resolved conversations into new knowledge for AI agents automation resolved conversations become new knowledge https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system automatically turns resolved conversations into new knowledge for AI agents F1-005-A015 0.0    
F1-005-S015 DeskcommCRM F1-005 The system lets a user apply an improvement the AI proposes for itself as a new agent version user-action **Proposals** are improvements the AI suggests for itself, applicable as a new version — always human-gated. https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets a user apply an improvement the AI proposes for itself as a new agent version F1-005-A016 0.0    
F1-005-S016 DeskcommCRM F1-005 The system lets a user configure the vocabulary of each pipeline, such as lead and won labels user-action configurable vocabulary per pipeline: a lead becomes a *Customer*, *Patient* or *Buyer* https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets a user configure the vocabulary of each pipeline, such as lead and won labels F1-005-A017 0.0    
F1-005-S017 DeskcommCRM F1-005 The system lets a user connect WhatsApp numbers by QR code user-action via **QR code** (WAHA, multi-number, with anti-ban: throttle + jitter + time windows) https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets a user connect WhatsApp numbers by QR code F1-005-A018 0.0    
F1-005-S018 DeskcommCRM F1-005 The system lets a user connect WhatsApp through an official business messaging channel user-action or through **Meta's official channel** (Cloud API, with approved templates kept in sync) https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets a user connect WhatsApp through an official business messaging channel F1-005-A019 0.0    
F1-005-S019 DeskcommCRM F1-005 The system automatically throttles and spaces WhatsApp sends within time windows to avoid bans automation anti-ban: throttle + jitter + time windows https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system automatically throttles and spaces WhatsApp sends within time windows to avoid bans F1-005-A020 0.0    
F1-005-S020 DeskcommCRM F1-005 The system automatically detects opt-out messages from contacts automation STOP detection https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 01.txt d3145a3a75f13bbf55b1495d42db6e1162a62cb95efc84786a9097c98cec5130 extract-a both confirmed The system automatically detects opt-out messages from contacts F1-005-A021 0.0    
F1-005-S021 DeskcommCRM F1-005 The system lets a user choose the AI provider at install time and switch later from the screen, per part of the system user-action decided at install time and switchable later from the screen, **per part of the system** https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets a user choose the AI provider at install time and switch later from the screen, per part of the system F1-005-A022 0.0    
F1-005-S022 DeskcommCRM F1-005 The system lets an organization set spending caps on AI usage user-action per-org spending caps https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets an organization set spending caps on AI usage F1-005-A023 0.0    
F1-005-S023 DeskcommCRM F1-005 The system automatically analyzes sentiment of conversations automation sentiment analysis https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system automatically analyzes sentiment of conversations F1-005-A024 0.0    
F1-005-S024 DeskcommCRM F1-005 The system lets a user assign a lead to an AI as well as to a person user-action AI as a first-class assignee https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets a user assign a lead to an AI as well as to a person F1-005-A025 0.0    
F1-005-S025 DeskcommCRM F1-005 The system lets a user control access with server-side roles user-action real server-side RBAC https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a a confirmed The system lets a user control access with server-side roles F1-005-A026 0.0    
F1-005-S026 DeskcommCRM F1-005 The system lets a user assign and transfer conversations with an audit record user-action audited assignment/transfer https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets a user assign and transfer conversations with an audit record F1-005-A027 0.0    
F1-005-S027 DeskcommCRM F1-005 The system automatically distributes conversations to agents in a round-robin queue automation round-robin queue https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system automatically distributes conversations to agents in a round-robin queue F1-005-A028 1.0 1.0 Distribution to agents implied; excerpt only 'round-robin queue'.
F1-005-S028 DeskcommCRM F1-005 The system automatically routes conversations by detected intent automation automatic intent routing https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system automatically routes conversations by detected intent F1-005-A029 0.0    
F1-005-S029 DeskcommCRM F1-005 The system lets an administrator limit what each role can see user-action per-role visibility scopes https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets an administrator limit what each role can see F1-005-A030 0.0    
F1-005-S030 DeskcommCRM F1-005 The system automatically keeps an append-only audit log of changes automation append-only audit log with 5-year retention https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a a confirmed The system automatically keeps an append-only audit log of changes F1-005-A031 0.0    
F1-005-S031 DeskcommCRM F1-005 The system lets a user anonymize personal data instead of deleting it user-action anonymization preferred over deletion https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets a user anonymize personal data instead of deleting it F1-005-A032 0.0    
F1-005-S032 DeskcommCRM F1-005 The system lets a user export personal data on request. user-action export and redact via workers, cascading anonymization, audited consent https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both corrected The system lets a user export and redact personal data on request F1-005-A033 0.0    
F1-005-S033 DeskcommCRM F1-005 The system lets a user enable optional two-step verification for sign-in user-action it is **optional** and lives in Settings › Security https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets a user enable optional two-step verification for sign-in F1-005-A034 0.0    
F1-005-S034 DeskcommCRM F1-005 The system lets a manager create capture sources that receive leads from external forms and tools into a chosen pipeline stage user-action Every tenant can create **capture sources**: a public endpoint (`/api/v1/webhooks/in/`) that receives leads from landing pages, custom forms or tools like Zapier/n8n via POST (JSON or `application/x-www-form-urlencoded`) and drops them straight into the chosen pipeline/stage https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets a manager create capture sources that receive leads from external forms and tools into a chosen pipeline stage F1-005-A037 0.0    
F1-005-S035 DeskcommCRM F1-005 The system lets a manager build WHEN/IF/THEN automation rules that add tags, move leads, assign agents, send WhatsApp messages or notify external systems user-action WHEN/IF/THEN rules that add tags, move leads, assign agents, send WhatsApp messages or notify external systems via outgoing webhooks https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets a manager build WHEN/IF/THEN automation rules that add tags, move leads, assign agents, send WhatsApp messages or notify external systems F1-005-A038 0.0    
F1-005-S036 DeskcommCRM F1-005 The system lets a manager fire a test lead through a capture source and see recent deliveries user-action fire a test lead, see recent deliveries https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets a manager fire a test lead through a capture source and see recent deliveries F1-005-A039 0.0    
F1-005-S037 DeskcommCRM F1-005 The system lets a manager view a timeline of each automation run and manually retry a failed external webhook call user-action **Activity** (a timeline of each run, with per-action results and manual retry when an external webhook call fails) https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets a manager view a timeline of each automation run and manually retry a failed external webhook call F1-005-A040 0.0    
F1-005-S038 DeskcommCRM F1-005 The system automatically creates new automation rules in a paused state until they are reviewed and enabled automation build rules, which are always born paused until reviewed and enabled https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system automatically creates new automation rules in a paused state until they are reviewed and enabled F1-005-A041 0.0    
F1-005-S039 DeskcommCRM F1-005 The system lets a user manage deals on a kanban board by funnel stage user-action **Kanban** (where each deal sits in the funnel) https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets a user manage deals on a kanban board by funnel stage F1-005-A042 0.0    
F1-005-S040 DeskcommCRM F1-005 The system lets a user manage contacts user-action **Contacts** https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets a user manage contacts F1-005-A043 0.0    
F1-005-S041 DeskcommCRM F1-005 The system lets a user manage pipelines with stages, business vocabulary and loss reasons user-action **Pipelines** (stages, business vocabulary and loss reasons) https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets a user manage pipelines with stages, business vocabulary and loss reasons F1-005-A044 0.0    
F1-005-S042 DeskcommCRM F1-005 The system lets a user save quick replies user-action **Quick replies** https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets a user save quick replies F1-005-A045 0.0    
F1-005-S043 DeskcommCRM F1-005 The system lets a user view funnel and per-agent performance metrics user-action **Performance** (funnel and per-agent metrics) https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets a user view funnel and per-agent performance metrics F1-005-A046 0.0    
F1-005-S044 DeskcommCRM F1-005 The system lets a user manage the organization team user-action **Team** https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets a user manage the organization team F1-005-A047 0.0    
F1-005-S045 DeskcommCRM F1-005 The system lets a user manage API tokens user-action **API Tokens** https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 01.txt d3145a3a75f13bbf55b1495d42db6e1162a62cb95efc84786a9097c98cec5130 extract-a both confirmed The system lets a user manage API tokens F1-005-A048 0.0    
F1-005-S046 DeskcommCRM F1-005 The system lets a user view and manage active sessions and recovery codes user-action **Security** (MFA, recovery codes, sessions) https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets a user view and manage active sessions and recovery codes F1-005-A049 0.0    
F1-005-S047 DeskcommCRM F1-005 The system lets a user view an audit log user-action **Audit Log** https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 01.txt d3145a3a75f13bbf55b1495d42db6e1162a62cb95efc84786a9097c98cec5130 extract-a both confirmed The system lets a user view an audit log F1-005-A050 0.0    
F1-005-S048 DeskcommCRM F1-005 The system lets a user manage the knowledge base used by AI agents user-action **Knowledge** (RAG) https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a both confirmed The system lets a user manage the knowledge base used by AI agents F1-005-A051 1.0 1.0 Use by AI agents from table group heading.
F1-005-S049 DeskcommCRM F1-005 The system lets a user update the application from the screen with an automatic database backup user-action takes a database backup by itself https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a a confirmed The system lets a user update the application from the screen with an automatic database backup F1-005-A053 0.0    
F1-005-S050 DeskcommCRM F1-005 The system automatically rolls back to the previous version when an update comes up broken automation If the new version comes up broken, the agent **rolls back to the previous image on its own** https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a a confirmed The system automatically rolls back to the previous version when an update comes up broken F1-005-A054 0.0    

Next page

Advanced export

JSON shape: default, array, newline-delimited, object

CSV options: 

CREATE TABLE [features] ([feature_id] TEXT PRIMARY KEY, [app_id] TEXT, [statement] TEXT, [form] TEXT, [excerpt] TEXT, [source_url] TEXT, [source_file] TEXT, [source_sha256] TEXT, [found_by] TEXT, [found_by_runs] TEXT, [verification] TEXT, [pipeline_id] TEXT, [audited] REAL, [audit_correct] REAL, [audit_note] TEXT, FOREIGN KEY ([app_id]) REFERENCES apps(app_id), FOREIGN KEY ([pipeline_id]) REFERENCES candidates(candidate_id));
CREATE INDEX [idx_features_app_id] ON [features]([app_id]);
CREATE INDEX [idx_features_verification] ON [features]([verification]);
CREATE INDEX [idx_features_form] ON [features]([form]);
CREATE INDEX [idx_features_found_by] ON [features]([found_by]);