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).

4 rows where app_id = "F1-005", form = "automation" and found_by = "extract-b" sorted by feature_id

✎ View and edit SQL

This data as json, CSV (advanced)

Suggested facets: source_url, source_file, source_sha256, audited

verification 2

found_by 1

  • extract-b · 4 ✖

form 1

  • automation · 4 ✖

audit_correct 1

app_id 1

  • DeskcommCRM · 4 ✖
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-S054 DeskcommCRM F1-005 The system automatically triggers automations when an AI agent handles a conversation. automation trigger automations https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-b b corrected The system lets an AI agent trigger automations F1-005-B004 1.0 1.0 Excerpt is a two-word fragment; AI-agent link from surrounding sentence, condition loosely paraphrased.
F1-005-S055 DeskcommCRM F1-005 The system automatically runs skills for an AI agent during a conversation when the agent decides to use them. automation skills the agent executes on its own mid-conversation https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-b b corrected The system lets an AI agent execute skills on its own in the middle of a conversation F1-005-B007 0.0    
F1-005-S056 DeskcommCRM F1-005 The system automatically keeps an operational memory that AI agents use when answering. automation operational memory https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt 75d6303f73d57b7255c0218c83e947c34862d7dff8412e7b47024c022395522e extract-b b corrected The system lets an AI agent keep an operational memory F1-005-B008 0.0    
F1-005-S064 DeskcommCRM F1-005 The system automatically identifies a customer’s history, orders and prior agreements when a message arrives automation Before any reply, the system already knows who this is: history, orders, what was agreed last time. https://deskcomm.com.br/en 02.txt 1bfa7ae4165a966bc9e1f62b8f5a54e829812cf2a67ce4e76471ad3d2fdc0c59 extract-b b confirmed The system automatically identifies a customer’s history, orders and prior agreements when a message arrives F1-005-B067 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]);