home / pub10

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).

19 rows where app_id = "F1-005", form = "automation" 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 1

  • confirmed 19

found_by 1

  • extract-a · 19 ✖

form 1

  • automation · 19 ✖

audit_correct 1

  • 1.0 1

app_id 1

  • DeskcommCRM · 19 ✖
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-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-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-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-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-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-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-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-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-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    
F1-005-S051 DeskcommCRM F1-005 The system automatically shows an update notification to the server owner when a new version exists automation the sidebar footer lights up **"Nova versão"** https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-a a confirmed The system automatically shows an update notification to the server owner when a new version exists F1-005-A055 0.0    

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]);
Powered by Datasette · Queries took 199.308ms · Data license: Not yet licensed — internal review only · Data source: Ahmed ElBatanony, Innopolis University